© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152431
    Prev
    Next
    INDEX
    Explanations

    Action items and next steps

    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_23_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
    非
    0.47
     пуль
    0.41
    /
    0.41
    盟
    0.41
    laz
    0.39
     забруд
    0.39
     масштаб
    0.38
    LIC
    0.38
     имущества
    0.38
     非
    0.38
    POSITIVE LOGITS
    coln
    0.43
    ിലാണ്
    0.42
     آقای
    0.40
     experi
    0.40
     Venkates
    0.40
     Bal
    0.39
     katıl
    0.39
     inté
    0.38
    قيق
    0.38
     Epp
    0.38
    Activations Density 0.000%

    No Known Activations