© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44130
    Prev
    Next
    INDEX
    Explanations

    Key presses for movement

    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_13_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
    қ
    0.19
    cz
    0.19
    tn
    0.19
    キス
    0.19
    /"+
    0.19
    q
    0.19
    bookings
    0.18
    affles
    0.18
    kut
    0.18
    kir
    0.18
    POSITIVE LOGITS
     Vir
    0.22
    瑄
    0.21
    㐱
    0.20
     Sanit
    0.20
     chiave
    0.20
    作为
    0.20
     Gave
    0.20
    酲
    0.20
     flagging
    0.20
    otá
    0.19
    Activations Density 0.005%

    No Known Activations