© 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. 36201
    Prev
    Next
    INDEX
    Explanations

    digital library, storytelling, image, painting, entertainment, communications

    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
    se
    0.81
    sthe
    0.68
     zing
    0.65
    straße
    0.63
    ता
    0.61
    สดง
    0.60
    .,"
    0.59
    স
    0.59
    お客様
    0.59
    Ро
    0.58
    POSITIVE LOGITS
    ه
    0.71
    in
    0.70
     not
    0.69
     \]
    0.69
     kullanıl
    0.66
    )،
    0.64
    ো
    0.62
    াষ
    0.62
     revital
    0.59
     முன்பு
    0.59
    Activations Density 0.022%

    No Known Activations