© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130713
    Prev
    Next
    INDEX
    Explanations

    aimed for a goal

    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_6_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
    ll
    1.15
     (
    0.99
    m
    0.99
    to
    0.99
    A
    0.96
    s
    0.94
    len
    0.93
    F
    0.90
    llan
    0.88
     langs
    0.87
    POSITIVE LOGITS
    ᱖
    1.12
    ᱕
    1.09
    ти
    1.06
    ᱓
    1.05
    ᱔
    0.97
    ка
    0.95
    ام
    0.94
    ů
    0.93
    ově
    0.92
    ᱗
    0.90
    Activations Density 0.003%

    No Known Activations