© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161306
    Prev
    Next
    INDEX
    Explanations

    difference between

    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_2_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
    ,
    1.05
    ية
    1.02
    -
    1.00
    其他
    0.97
     etwa
    0.93
    .
    0.91
    B
    0.83
    ில்
    0.83
    X
    0.82
    ation
    0.81
    POSITIVE LOGITS
    ۹
    1.05
    latency
    0.93
     vutto
    0.89
    concepto
    0.88
    ρων
    0.88
    gesture
    0.86
    goes
    0.84
    ष्टी
    0.83
    f
    0.83
    𝘱
    0.82
    Activations Density 0.008%

    No Known Activations