© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176491
    Prev
    Next
    INDEX
    Explanations

    user/assistant conversation delimiters

    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_24_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
     exceptions
    0.43
     exception
    0.42
     invitations
    0.41
     getUsers
    0.39
     пользователей
    0.38
    usuarios
    0.37
     wyją
    0.37
    遣
    0.37
    CHARGE
    0.37
     fileCopy
    0.36
    POSITIVE LOGITS
     ಕರ್ನಾಟಕ
    0.45
    ྛ
    0.45
    érica
    0.44
    inat
    0.42
     جناح
    0.42
    बद्ध
    0.41
    iflor
    0.40
     कर्नाटक
    0.39
     Hrvatskoj
    0.39
    Trends
    0.38
    Activations Density 0.005%

    No Known Activations