© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118395
    Prev
    Next
    INDEX
    Explanations

    suggestion for next step

    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_27_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
    izamos
    0.42
     Mé
    0.42
    Ғ
    0.40
    prometheus
    0.40
    상을
    0.39
    ições
    0.39
     cookware
    0.38
     상
    0.38
     paras
    0.38
     한
    0.37
    POSITIVE LOGITS
    ，“
    0.37
    ,—
    0.37
     prawdopod
    0.36
    成長
    0.36
     ஆரம்ப
    0.36
     Reclamation
    0.35
     可能
    0.34
     swimmers
    0.34
     posible
    0.34
    可能
    0.33
    Activations Density 0.000%

    No Known Activations