© 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. 220298
    Prev
    Next
    INDEX
    Explanations

    for sale or for parts

    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
     акысыз
    0.40
     용
    0.39
     removable
    0.39
     }));
    0.37
     جنوبی
    0.37
    憉
    0.37
    宓
    0.37
    Removed
    0.36
    に入れて
    0.36
    移除
    0.36
    POSITIVE LOGITS
    гор
    0.41
     luk
    0.40
     Luk
    0.39
     queste
    0.39
    affer
    0.37
     BLAST
    0.36
    gara
    0.36
     görev
    0.36
     blast
    0.35
    ͍
    0.35
    Activations Density 0.000%

    No Known Activations