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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3685
    Prev
    Next
    INDEX
    Explanations

    hyphens and numbers, common grammatical constructs, words within parentheses

    oai_token-act-pair · gemini-2.0-flash

    hyphens/parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WebElementEntity
    -0.57
    he
    -0.52
    vc
    -0.50
    v
    -0.45
     talle
    -0.43
    here
    -0.41
    QUADS
    -0.40
    we
    -0.40
     don
    -0.38
    放到
    -0.38
    POSITIVE LOGITS
     مشين
    0.75
     &___
    0.75
     betweenstory
    0.73
    OGND
    0.73
    RenderAtEndOf
    0.68
     Roskov
    0.68
    Datuak
    0.67
    principalTable
    0.66
     ProtoMessage
    0.65
    Geplaatst
    0.60
    Activations Density 8.510%

    No Known Activations