© 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. 122971
    Prev
    Next
    INDEX
    Explanations

    misunderstanding

    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
    '";
    0.80
     Gerade
    0.72
     سي
    0.68
    u
    0.68
    '$\
    0.65
    '/>
    0.64
    '};
    0.63
    ৬
    0.62
    ٠
    0.62
    '}}
    0.61
    POSITIVE LOGITS
    t
    0.84
    le
    0.59
    żli
    0.55
    efeller
    0.54
    y
    0.54
    ย
    0.54
     excess
    0.53
    ที่มี
    0.53
    fulness
    0.52
    𝘆
    0.51
    Activations Density 0.000%

    No Known Activations