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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    acknowledgements, funding sources and legal disclaimers

    oai_token-act-pair · gemini-2.0-flash

    acknowledgements

    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
    <bos>
    -0.55
    due
    -0.45
     due
    -0.42
    r
    -0.40
     regla
    -0.39
     šķ
    -0.39
    AutoresizingMask
    -0.38
     «
    -0.38
     N
    -0.38
    pa
    -0.38
    POSITIVE LOGITS
     >=",
    0.91
    StoryboardSegue
    0.86
     Theſe
    0.85
    __.__
    0.84
     HasFactory
    0.81
    PreferredItem
    0.80
    sidemargin
    0.79
     صوتيه
    0.78
     للمعارف
    0.77
    ABAJO
    0.77
    Activations Density 0.130%

    No Known Activations