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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3263
    Prev
    Next
    INDEX
    Explanations

    technical writing describing the objects and goals of an invention.

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
     object
    -2.58
     Object
    -2.50
     Objects
    -2.41
     objects
    -2.34
    object
    -2.31
     OBJECT
    -2.31
    Object
    -2.28
    Objects
    -2.16
    objects
    -2.11
    obj
    -2.08
    POSITIVE LOGITS
    tagHelperRunner
    0.68
     an
    0.64
     versa
    0.49
     صوتيه
    0.49
    GraphicsUnit
    0.48
    unistd
    0.46
     архивлан
    0.46
    onk
    0.45
    seiti
    0.44
     Brem
    0.44
    Activations Density 1.869%

    No Known Activations