© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136828
    Prev
    Next
    INDEX
    Explanations

    anchor chain

    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_12_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
    s
    0.59
    Prevention
    0.57
    W
    0.57
     우리는
    0.56
    Protection
    0.54
    variant
    0.54
    Defense
    0.54
    diabetes
    0.54
    with
    0.54
    sin
    0.53
    POSITIVE LOGITS
     Aloha
    0.63
     Anchor
    0.51
     Gates
    0.50
     terrazzo
    0.50
    彿
    0.50
     Grange
    0.50
     SPAC
    0.50
     peque
    0.49
    𒋀
    0.49
     Sha
    0.49
    Activations Density 0.000%

    No Known Activations