© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236008
    Prev
    Next
    INDEX
    Explanations

    numbers followed by year delimiters

    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_25_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
    齦
    0.37
     hyster
    0.37
    訊
    0.36
    ủi
    0.36
    deployment
    0.36
    topping
    0.35
    geolocation
    0.35
     flattening
    0.35
     stella
    0.34
     katth
    0.34
    POSITIVE LOGITS
     Successfully
    0.41
     InMemory
    0.34
    候
    0.34
    Listo
    0.34
    ABLISHED
    0.34
     তালিকা
    0.33
    ッフ
    0.33
    ㅇ
    0.32
    枌
    0.32
     bequeathed
    0.32
    Activations Density 0.009%

    No Known Activations