© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91176
    Prev
    Next
    INDEX
    Explanations

    apple beginning

    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_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
    지
    0.81
    is
    0.81
    G
    0.74
    D
    0.72
    та
    0.70
    ap
    0.69
    いる
    0.69
    را
    0.68
    urban
    0.68
    s
    0.67
    POSITIVE LOGITS
     in
    0.84
     it
    0.72
     quell
    0.64
     modelo
    0.64
     carro
    0.64
     stell
    0.63
     accesso
    0.63
     permet
    0.63
     lab
    0.62
     regist
    0.62
    Activations Density 0.000%

    No Known Activations