© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202118
    Prev
    Next
    INDEX
    Explanations

    ngrok alternatives

    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_6_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
    ও
    0.94
    kowe
    0.90
    '
    0.84
    ट
    0.82
    ième
    0.81
    ची
    0.79
    2
    0.79
    globe
    0.77
     possono
    0.74
     mogą
    0.74
    POSITIVE LOGITS
     for
    1.11
     I
    0.99
     It
    0.91
     with
    0.87
    ít
    0.85
     сдела
    0.84
    I
    0.83
    服务
    0.82
    多
    0.82
    ien
    0.80
    Activations Density 0.000%

    No Known Activations