© 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. 5259
    Prev
    Next
    INDEX
    Explanations

    the token sequence `cho` followed by another character like "ck", "an", "cta", etc

    oai_token-act-pair · gemini-2.0-flash

    cho

    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
     bows
    -0.49
    writeString
    -0.46
     troughs
    -0.45
    vosť
    -0.44
    Contexts
    -0.43
     enx
    -0.42
    روض
    -0.42
     miệng
    -0.42
     cittad
    -0.41
    ajú
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.89
    ագրություններ
    0.73
     Roskov
    0.72
    bootstrapcdn
    0.69
     Reverso
    0.64
    таратура
    0.64
     ويكيپيديا
    0.64
    Sucesor
    0.62
    <?
    0.62
     Мексичка
    0.60
    Activations Density 0.427%

    No Known Activations