© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216317
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    𝐫
    0.46
    Ny
    0.43
     Ny
    0.41
    OwnProperty
    0.38
    miri
    0.38
     Vidy
    0.37
    ग्रियों
    0.37
    𖤐
    0.37
    ত্তির
    0.37
    ологии
    0.37
    POSITIVE LOGITS
    ambers
    0.43
    мережа
    0.42
    given
    0.36
    ぞ
    0.35
    ifts
    0.34
    ifo
    0.34
    américa
    0.34
     given
    0.34
    ukh
    0.34
    blo
    0.33
    Activations Density 0.002%

    No Known Activations