© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13588
    Prev
    Next
    INDEX
    Explanations

    the word "on".

    oai_token-act-pair · gemini-2.0-flash

    On

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     wyb
    -0.39
    ¿
    -0.35
    用意
    -0.35
    mtable
    -0.33
    pb
    -0.33
    ლ
    -0.33
    <h3>
    -0.32
    requireNonNull
    -0.32
     converted
    -0.32
    gol
    -0.32
    POSITIVE LOGITS
    AndEndTag
    1.05
    ConstraintMaker
    0.98
    oredCriteria
    0.94
    twimg
    0.91
     unknownFields
    0.85
    verwijspagina
    0.82
     mergeFrom
    0.82
    principalColumn
    0.81
     يتيمه
    0.81
    bewerken
    0.79
    Activations Density 0.663%

    No Known Activations