© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1796
    Prev
    Next
    INDEX
    Explanations

    start of turn

    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_39_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
    alee
    0.40
    êté
    0.39
     Zeal
    0.38
    oster
    0.38
     अध्या
    0.38
    }"),
    0.38
    が入
    0.37
     upwards
    0.37
    enthal
    0.36
     (>
    0.36
    POSITIVE LOGITS
     இறு
    0.41
    Westinghouse
    0.40
    HCO
    0.38
    Basic
    0.36
    وَ
    0.36
    广大
    0.36
     Each
    0.36
    TiO
    0.36
     देऊ
    0.36
    equivariant
    0.36
    Activations Density 0.085%

    No Known Activations