© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58797
    Prev
    Next
    INDEX
    Explanations

    compile the code

    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_2_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
    rik
    1.19
    ాలు
    1.15
    ige
    1.10
    ూ
    1.06
    ία
    1.04
     गहरा
    1.02
    ension
    1.01
    ern
    1.00
    itta
    0.98
    cent
    0.97
    POSITIVE LOGITS
    a
    2.16
    ه
    1.91
    is
    1.79
    o
    1.63
    া
    1.56
    u
    1.52
    ה
    1.47
    at
    1.46
    an
    1.44
    x
    1.41
    Activations Density 0.001%

    No Known Activations