© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259082
    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
     jumlah
    1.39
     discoloration
    1.37
     दिसून
    1.35
    radiation
    1.33
    reactant
    1.32
     lotion
    1.32
     ridiculus
    1.31
    戤
    1.31
    блиоте
    1.31
    𝐬
    1.31
    POSITIVE LOGITS
    as
    1.23
    ‑
    1.22
    es
    1.14
    it
    1.14
    a
    1.13
    os
    1.12
    i
    1.05
    ocl
    1.01
    소
    0.99
    Rez
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.