© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90262
    Prev
    Next
    INDEX
    Explanations

    hypothetical conditions

    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_11_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
    ње
    0.72
    и
    0.71
    inde
    0.64
    𝕕
    0.63
     эффективность
    0.63
    на
    0.60
    OD
    0.60
    оне
    0.59
    توى
    0.59
     रैम
    0.59
    POSITIVE LOGITS
    :
    0.72
     okolic
    0.55
    zk
    0.54
    sek
    0.52
    </strong>
    0.52
     I
    0.52
     C
    0.49
     Z
    0.49
     আসছে
    0.49
     KOH
    0.49
    Activations Density 0.005%

    No Known Activations