© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167038
    Prev
    Next
    INDEX
    Explanations

    place as prison

    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_31_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
    Crossing
    0.40
    Optim
    0.38
    泡
    0.37
    Hik
    0.36
    optim
    0.35
    Spread
    0.35
    cyano
    0.35
     optimality
    0.35
     সূচনা
    0.35
    ۚ
    0.34
    POSITIVE LOGITS
     punishment
    0.67
     punish
    0.61
     banished
    0.56
     punished
    0.54
    惩
    0.54
     punitive
    0.53
     punishing
    0.53
     dumping
    0.52
     punishments
    0.52
     relegated
    0.51
    Activations Density 0.047%

    No Known Activations