© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6245
    Prev
    Next
    INDEX
    Explanations

    parenthetical context and names of places and people, as well as typographical elements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     the
    -0.63
     I
    -0.55
     You
    -0.50
     The
    -0.50
     a
    -0.50
     We
    -0.50
     It
    -0.50
     They
    -0.49
     one
    -0.48
     This
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     BrowserModule
    0.72
     ProtoMessage
    0.71
    AnchorStyles
    0.70
    bootstrapcdn
    0.69
     فريبيس
    0.68
     ddelweddau
    0.65
     CreateTagHelper
    0.65
     utafitiHapana
    0.64
    RenderAtEndOf
    0.64
    Activations Density 11.320%

    No Known Activations