© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45678
    Prev
    Next
    INDEX
    Explanations

    database connection config

    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_22_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
    츄
    0.22
     samples
    0.21
    プチ
    0.21
     bajas
    0.21
     Nisha
    0.21
    팰
    0.21
     Nai
    0.21
     cholinergic
    0.21
    㴡
    0.21
    WERS
    0.21
    POSITIVE LOGITS
    OT
    0.25
    ொ
    0.23
    进
    0.23
    ‘
    0.22
    आईएस
    0.22
    ickey
    0.22
    आईपी
    0.22
    ítica
    0.22
     pace
    0.21
    佽
    0.21
    Activations Density 0.004%

    No Known Activations