© 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. 86570
    Prev
    Next
    INDEX
    Explanations

    Low Power Noise Amplifier

    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
    erweise
    0.70
    עות
    0.66
     Asht
    0.66
    \}.
    0.65
    ہ
    0.65
     заяви
    0.63
    }());
    0.62
    б
    0.62
    anze
    0.62
    ాలు
    0.61
    POSITIVE LOGITS
    on
    1.06
    ON
    1.05
    AN
    0.85
    low
    0.81
    IN
    0.79
    PL
    0.78
    small
    0.77
     low
    0.77
    LOW
    0.77
    t
    0.76
    Activations Density 0.002%

    No Known Activations