Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261174
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rename
    1.26
    )}}
    1.22
    з
    1.22
     Airlines
    1.20
    ೆ
    1.20
    )}$,
    1.17
    urbance
    1.14
     Reasoning
    1.14
    )$,
    1.14
    ratulations
    1.11
    POSITIVE LOGITS
    umé
    1.32
     لقد
    1.31
     lä
    1.29
     abut
    1.25
     değişik
    1.24
    કમ
    1.24
    bär
    1.22
    ierend
    1.19
     decía
    1.18
     percaya
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.