© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198174
    Prev
    Next
    INDEX
    Explanations

    cherry-picking

    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_4_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
    on
    0.98
    l
    0.96
    ल
    0.84
    n
    0.82
    ل
    0.82
    ”
    0.76
    на
    0.76
    nání
    0.76
    ).
    0.75
    ל
    0.74
    POSITIVE LOGITS
    ح
    0.88
    ıları
    0.82
    ंक्शन
    0.79
    s
    0.79
     conjuntos
    0.77
     julho
    0.75
     accumulate
    0.73
     assass
    0.73
    ly
    0.73
     poziom
    0.73
    Activations Density 0.000%

    No Known Activations