© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9225
    Prev
    Next
    INDEX
    Explanations

    private schools, flagship campuses, state universities, compound semiconductors

    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_13_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
    入了
    0.37
    }$
    0.36
     egg
    0.36
     novas
    0.36
    }$.
    0.35
     trứng
    0.34
     Egg
    0.33
     Oc
    0.33
    }$,
    0.32
    nearly
    0.32
    POSITIVE LOGITS
    یکن
    0.40
    লেখ
    0.40
     aloud
    0.39
    é
    0.39
     জোট
    0.38
     reunir
    0.38
     coerce
    0.38
    කර
    0.37
     Lantern
    0.37
     coercion
    0.37
    Activations Density 0.025%

    No Known Activations