© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8929
    Prev
    Next
    INDEX
    Explanations

    garnish with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    скага
    2.08
    𝒓
    1.97
     וי
    1.92
    𝙚
    1.91
     跳转
    1.90
     сприя
    1.89
     vyh
    1.85
     maju
    1.82
    forma
    1.82
    keun
    1.81
    POSITIVE LOGITS
    at
    2.61
    €™
    2.50
    to
    2.42
    fprintf
    2.39
    an
    2.18
     zich
    2.12
    𝘵
    2.06
     tannins
    1.95
    На
    1.94
    на
    1.94
    Activations Density 0.003%

    No Known Activations