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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6660
    Prev
    Next
    INDEX
    Explanations

    the word "real" and words/characters directly connected to it.

    oai_token-act-pair · gemini-2.0-flash

    words related to real experiences

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

    real

    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
    发表于
    -0.58
     actually
    -0.58
    actually
    -0.52
     faktiskt
    -0.51
    ChildScrollView
    -0.50
     flesta
    -0.49
     Actually
    -0.47
    Actually
    -0.47
     lèvres
    -0.47
     AttributeSet
    -0.46
    POSITIVE LOGITS
     houſe
    0.75
    StoryboardSegue
    0.73
     purpoſe
    0.68
     Shakspeare
    0.66
     pleaſure
    0.66
    hability
    0.65
     ſta
    0.64
    oredCriteria
    0.64
    IsContent
    0.64
     Jefus
    0.63
    Activations Density 1.892%

    No Known Activations