© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123559
    Prev
    Next
    INDEX
    Explanations

    size of

    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
    er
    0.72
    <
    0.66
    the
    0.66
    2
    0.64
    ने
    0.62
    .
    0.62
    gung
    0.61
    LE
    0.60
    $.
    0.60
    >
    0.59
    POSITIVE LOGITS
    </h3>
    0.63
     cheeky
    0.62
    </h4>
    0.61
    </h6>
    0.60
     equipos
    0.57
    </i>
    0.57
     pierde
    0.57
    いた
    0.56
    ">(</
    0.55
    いない
    0.55
    Activations Density 0.001%

    No Known Activations