© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9104
    Prev
    Next
    INDEX
    Explanations

    titles and names

    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
    糺
    0.47
    蛜
    0.46
     OSA
    0.44
     必ず
    0.43
     Cannes
    0.42
     tokamaks
    0.42
     SCA
    0.41
    鞆
    0.41
    蚛
    0.41
     EMA
    0.40
    POSITIVE LOGITS
    if
    0.45
    People
    0.40
    Sb
    0.40
    ial
    0.38
     người
    0.38
    ।
    0.37
    io
    0.37
    olved
    0.36
    ieu
    0.36
    P
    0.36
    Activations Density 0.014%

    No Known Activations