© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16173
    Prev
    Next
    INDEX
    Explanations

    the characters "sc"

    oai_token-act-pair · gemini-2.0-flash

    sc

    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
    der
    -0.52
    herokuapp
    -0.50
     qu
    -0.49
    vertre
    -0.47
    ViewHolder
    -0.47
    googleapis
    -0.46
    gs
    -0.45
    agama
    -0.45
    mischer
    -0.45
    ⓘ
    -0.45
    POSITIVE LOGITS
    zbęd
    0.69
     Efq
    0.69
     itſelf
    0.67
     Theſe
    0.66
     كومونز
    0.65
     يتيمه
    0.65
    InputBorder
    0.65
    észetes
    0.63
     pleaſure
    0.62
     Anſ
    0.62
    Activations Density 0.500%

    No Known Activations