© 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. 6761
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Math/Scientific formulas

    np_max-act-logits · 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
    NUMX
    -0.75
     themſelves
    -0.73
     poffible
    -0.70
     Efq
    -0.70
     ſtate
    -0.69
     iſt
    -0.69
     purpoſe
    -0.68
     Majefty
    -0.66
     Theſe
    -0.66
    0
    -0.66
    POSITIVE LOGITS
     surla
    0.45
     "..\..\..\
    0.44
     INTERESAR
    0.42
     noten
    0.42
    zija
    0.41
     getItemCount
    0.41
    ⓧ
    0.40
     للمعارف
    0.40
    gnus
    0.38
    kuuta
    0.38
    Activations Density 9.379%

    No Known Activations