© 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. 209050
    Prev
    Next
    INDEX
    Explanations

    team

    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
     ά
    0.41
     Antit
    0.41
    ]$,
    0.40
     Meanwhile
    0.40
     язы
    0.39
     જેવા
    0.38
     রয়ে
    0.38
     ঋ
    0.38
     সহজ
    0.38
    吁
    0.38
    POSITIVE LOGITS
    كب
    0.40
     पाना
    0.40
    gono
    0.40
    ramos
    0.39
    concept
    0.38
     konsep
    0.38
    preprocessing
    0.37
     studies
    0.37
    concern
    0.37
    branched
    0.37
    Activations Density 0.004%

    No Known Activations