© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137179
    Prev
    Next
    INDEX
    Explanations

    plants and flowers

    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_12_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
    ării
    0.55
     तानाशाह
    0.54
    cinoma
    0.53
    ;',
    0.53
     مخصوص
    0.53
    가가
    0.52
    전에
    0.51
     presenceData
    0.51
    ających
    0.50
    äfte
    0.50
    POSITIVE LOGITS
     l
    0.50
     create
    0.50
    e
    0.49
    all
    0.47
    న్యూ
    0.47
     they
    0.46
     logins
    0.46
    ALL
    0.46
     work
    0.46
     really
    0.46
    Activations Density 0.000%

    No Known Activations