© 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. 42689
    Prev
    Next
    INDEX
    Explanations

    voice actors

    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
    I
    0.76
    n
    0.73
    In
    0.67
    </h4>
    0.66
    </h3>
    0.66
    AL
    0.65
    h
    0.63
    Us
    0.62
    you
    0.62
    </h1>
    0.60
    POSITIVE LOGITS
     for
    0.67
     sanitized
    0.63
     traveling
    0.61
     rematch
    0.60
    ३
    0.60
    raiser
    0.58
     on
    0.57
     rotated
    0.57
     bowled
    0.56
     হইবার
    0.55
    Activations Density 0.004%

    No Known Activations