© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42119
    Prev
    Next
    INDEX
    Explanations

    emerging from

    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
    l
    0.82
    ah
    0.65
    h
    0.63
    as
    0.63
    ت
    0.62
    ل
    0.60
    al
    0.59
    0.59
    us
    0.58
    <0x0D>
    0.57
    POSITIVE LOGITS
    カ
    0.69
    не
    0.68
     emerging
    0.67
     emerged
    0.66
    чают
    0.65
     emergencia
    0.64
     डैश
    0.64
     کا
    0.63
     کار
    0.63
    ﺪ
    0.61
    Activations Density 0.004%

    No Known Activations