Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12670
    Prev
    Next
    INDEX
    Explanations

    Java stack traces

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    GraphicsUnit
    -1.03
    AutoresizingMask
    -1.02
    Autoritní
    -1.00
    bootstrapcdn
    -0.91
     autorytatywna
    -0.91
    rungsseite
    -0.91
     utafitiHapana
    -0.88
    Tikang
    -0.88
     متعلقه
    -0.88
    ThroughAttribute
    -0.87
    POSITIVE LOGITS
     conna
    0.46
     it
    0.41
     the
    0.41
     vermelho
    0.40
     that
    0.39
     about
    0.37
     their
    0.36
    AVES
    0.36
     any
    0.35
     ges
    0.35
    Activations Density 0.837%

    No Known Activations