© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59144
    Prev
    Next
    INDEX
    Explanations

    movies or films

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Director
    0.42
     Shows
    0.40
     Director
    0.40
    자는
    0.38
     Portion
    0.38
    Sets
    0.36
     Umfang
    0.36
    拟
    0.35
     табу
    0.35
    ены
    0.35
    POSITIVE LOGITS
     adaptation
    1.46
     adaption
    1.31
    adaptation
    1.30
     Adaptation
    1.18
     adaptations
    1.06
     adaptación
    1.05
     adapta
    0.91
     adapt
    0.89
     adapter
    0.85
    adapt
    0.80
    Activations Density 0.007%

    No Known Activations