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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256783
    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
    ра
    1.37
     основные
    1.30
    दित
    1.24
    ยืน
    1.19
     laissant
    1.16
     concluding
    1.16
    €™
    1.16
     inilah
    1.14
    頤
    1.12
    вання
    1.08
    POSITIVE LOGITS
    ounge
    1.53
    night
    1.43
    pickle
    1.22
    𝓮
    1.21
    ..\
    1.20
    ∕
    1.18
    chunks
    1.15
    pepper
    1.14
    nte
    1.12
     xref
    1.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.