© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9767
    Prev
    Next
    INDEX
    Explanations

    parts of names

    oai_token-act-pair · gemini-2.0-flash

    hon

    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>
    -0.74
    нти
    -0.52
     ""],
    -0.47
     Thread
    -0.46
     imp
    -0.45
     Blood
    -0.44
    ROIT
    -0.44
     though
    -0.43
     Fuchs
    -0.43
     dit
    -0.43
    POSITIVE LOGITS
     propOrder
    0.77
    fjspx
    0.75
     Roskov
    0.70
     ModelExpression
    0.69
    OGND
    0.67
     الرياضيه
    0.65
    enterOuterAlt
    0.64
     defaultstate
    0.64
     للاسماء
    0.64
     kasarigan
    0.62
    Activations Density 0.315%

    No Known Activations