© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89186
    Prev
    Next
    INDEX
    Explanations

    To Kill a Mockingbird

    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_11_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
    0.66
    al
    0.63
    was
    0.59
    plant
    0.59
    agonist
    0.58
    of
    0.58
    various
    0.57
    them
    0.57
    repet
    0.56
    may
    0.56
    POSITIVE LOGITS
     قاف
    0.55
     केली
    0.52
     airson
    0.52
    বিমান
    0.51
    跏
    0.50
    贷款
    0.50
    貸款
    0.50
    Ꮙ
    0.50
     авиа
    0.49
    航空
    0.49
    Activations Density 0.000%

    No Known Activations