© 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. 31560
    Prev
    Next
    INDEX
    Explanations

    username credential claims

    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
     метал
    0.24
    łow
    0.24
     danneggi
    0.24
    јо
    0.24
    uere
    0.24
    neutral
    0.23
    조
    0.23
    λί
    0.22
    repe
    0.22
     нейтра
    0.22
    POSITIVE LOGITS
     samud
    0.24
     Couple
    0.23
     Congratulations
    0.22
     Dend
    0.22
     sumptuous
    0.22
     seab
    0.22
    בור
    0.22
    сини
    0.22
     modelling
    0.22
     logins
    0.22
    Activations Density 0.001%

    No Known Activations