© 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. 9203
    Prev
    Next
    INDEX
    Explanations

    `<script>` alert

    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
    Negative Logits
    деся
    2.31
    また
    2.30
    м
    2.24
     ώστε
    2.13
     inflicted
    2.11
     conexion
    2.07
    कुछ
    2.04
     attn
    2.00
    ಂದ್ರ
    1.97
    στη
    1.96
    POSITIVE LOGITS
    ात
    2.47
    malign
    2.22
    ванням
    2.19
    it
    2.17
    je
    2.08
    tahun
    2.08
    ى
    2.06
    गर
    2.06
    hounds
    2.05
    meric
    2.05
    Activations Density 0.022%

    No Known Activations