© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169266
    Prev
    Next
    INDEX
    Explanations

    mixed text

    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_56_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
    pective
    0.28
     t
    0.27
     chromatography
    0.27
     god
    0.26
     naphthalene
    0.26
     調
    0.25
     advantageous
    0.25
     flav
    0.24
     hack
    0.24
     electro
    0.24
    POSITIVE LOGITS
    лих
    0.27
    лей
    0.27
     benötigen
    0.27
    Come
    0.27
    LIKE
    0.27
     бес
    0.26
    Все
    0.26
    Elig
    0.26
     Hör
    0.26
    %).
    0.26
    Activations Density 0.000%

    No Known Activations