© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44335
    Prev
    Next
    INDEX
    Explanations

    hutongs

    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_3_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
     and
    0.66
    <0xB9>
    0.65
    ून
    0.65
    ку
    0.63
     genotypes
    0.59
    з
    0.58
    ために
    0.56
    های
    0.55
    ശാല
    0.55
    ים
    0.54
    POSITIVE LOGITS
    ;
    0.66
     penge
    0.60
    ↵
    0.59
     Πε
    0.59
     calific
    0.57
     funkci
    0.53
    <0x0D>
    0.52
     NI
    0.52
     Parlament
    0.52
     Mỗi
    0.52
    Activations Density 0.000%

    No Known Activations