© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161826
    Prev
    Next
    INDEX
    Explanations

    needs to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     defenders
    0.37
     backups
    0.37
     maintenance
    0.37
     умолча
    0.35
    裱
    0.35
     base
    0.35
     பாது
    0.35
     oun
    0.34
    还没有
    0.34
     பார்
    0.33
    POSITIVE LOGITS
    ჰ
    0.48
     غذ
    0.38
    вина
    0.37
    感到
    0.37
    ructor
    0.37
    ونی
    0.37
     richting
    0.36
    हेलो
    0.36
     siente
    0.36
    يدي
    0.36
    Activations Density 0.004%

    No Known Activations