© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196232
    Prev
    Next
    INDEX
    Explanations

    role-playing games

    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_27_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
    }}}\
    0.46
    premi
    0.44
     Uninstall
    0.41
    dll
    0.40
    elih
    0.38
    elhos
    0.38
     GeForce
    0.38
     circost
    0.37
    峒
    0.37
     fluence
    0.37
    POSITIVE LOGITS
    ೃಷ್ಟ
    0.40
     Mamm
    0.38
    ｱ
    0.37
     Laff
    0.36
    ირ
    0.36
     bribery
    0.35
    を進
    0.35
    買う
    0.35
    発達
    0.34
    していく
    0.34
    Activations Density 0.010%

    No Known Activations