© 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-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245365
    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_11_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
    na
    1.18
    ই
    1.14
    رو
    1.12
    可以将
    1.09
    可以
    1.06
    tie
    1.02
    tails
    1.00
     actuator
    1.00
    مون
    1.00
    dyn
    1.00
    POSITIVE LOGITS
     lawan
    1.22
     lhe
    1.17
     terecht
    1.15
     ehe
    1.12
     pikir
    1.11
    랗
    1.05
    coherent
    1.05
     kanamycin
    1.04
     demean
    1.02
    getting
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.