© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45476
    Prev
    Next
    INDEX
    Explanations

    . / authority / Not

    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_13_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
    parseLong
    0.55
    SCHRAMM
    0.47
     andRow
    0.47
    TEGER
    0.46
    ปี
    0.46
    प
    0.45
    на
    0.44
    UX
    0.44
    вых
    0.43
    vens
    0.43
    POSITIVE LOGITS
     Not
    0.44
    ettamente
    0.44
     పి
    0.43
    dQ
    0.43
    ionario
    0.43
    liste
    0.42
     legislate
    0.41
     cart
    0.40
    Not
    0.40
     finances
    0.40
    Activations Density 0.000%

    No Known Activations