© 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-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53498
    Prev
    Next
    INDEX
    Explanations

    a zero

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     þe
    0.44
     (%
    0.42
    (%
    0.40
     percent
    0.39
    
    0.38
    త్తు
    0.37
     →
    0.36
     þ
    0.36
    ?:
    0.36
     moelle
    0.36
    POSITIVE LOGITS
     முற
    0.37
     শারীর
    0.36
    MOV
    0.36
     functionally
    0.35
    দায়
    0.35
    純
    0.34
    })"
    0.34
     ನಡೆ
    0.34
    商品は
    0.34
    *************
    0.33
    Activations Density 0.006%

    No Known Activations