© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4242
    Prev
    Next
    INDEX
    Explanations

    words and phrases common in the context of discussing role-playing games

    oai_token-act-pair · gemini-2.0-flash

    diverse terms or concepts related to role-playing games (RPGs)

    np_token-act-pair-logits · gpt-4o-mini

    Sentence fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.50
     blancos
    -0.50
    GEBURTS
    -0.47
    FailureListener
    -0.45
    ToolStripButton
    -0.44
    principalColumn
    -0.44
     primas
    -0.43
     Савез
    -0.42
    endregion
    -0.42
    ukup
    -0.42
    POSITIVE LOGITS
    BufferException
    0.63
    ſelf
    0.59
     Pad
    0.56
    الحياه
    0.55
    лактика
    0.55
    onomía
    0.55
    TypedDataSet
    0.53
     مخطط
    0.53
     Götter
    0.53
     generals
    0.52
    Activations Density 8.106%

    No Known Activations