© 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. 41991
    Prev
    Next
    INDEX
    Explanations

    Wall Art / achia

    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
    ल
    0.84
    لى
    0.80
    বি
    0.76
    ला
    0.75
    ل
    0.73
    я
    0.70
    ี
    0.68
    دو
    0.67
    ল
    0.64
    <0x0D>
    0.64
    POSITIVE LOGITS
    i
    0.75
     be
    0.73
    ி
    0.66
    h
    0.63
    ە
    0.63
     bombshell
    0.62
     I
    0.62
     of
    0.61
    ᓂ
    0.61
    ured
    0.59
    Activations Density 0.002%

    No Known Activations