© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5918
    Prev
    Next
    INDEX
    Explanations

    run commands

    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_39_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
    Store
    0.39
     сосе
    0.39
    Tie
    0.36
    Learning
    0.36
    Neighbors
    0.36
    匈
    0.36
    Handle
    0.35
     Knee
    0.35
    Heating
    0.35
    Genres
    0.34
    POSITIVE LOGITS
     invite
    0.44
     invites
    0.40
    惯
    0.40
    cado
    0.39
     INV
    0.38
    invite
    0.36
     task
    0.36
     cue
    0.36
     invit
    0.35
     Invite
    0.35
    Activations Density 0.028%

    No Known Activations