© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218505
    Prev
    Next
    INDEX
    Explanations

    site level talk approved

    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_16_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
     Hat
    0.59
     Decode
    0.55
    s
    0.54
     Brave
    0.53
     Die
    0.52
    R
    0.52
     LET
    0.51
     Hatch
    0.51
     Sink
    0.50
     Let
    0.50
    POSITIVE LOGITS
    心理
    0.52
    годи
    0.48
    нти
    0.46
     diner
    0.46
    льності
    0.46
    দা
    0.46
    同
    0.45
    新
    0.44
    ження
    0.44
     therapists
    0.44
    Activations Density 0.000%

    No Known Activations