© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194541
    Prev
    Next
    INDEX
    Explanations

    Midwest, West, Northeast, Coast

    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_15_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
    }
    0.19
    NESOTA
    0.17
    蹉
    0.16
    }.
    0.16
    plications
    0.16
     Docsity
    0.15
     M
    0.15
     educating
    0.15
     introspection
    0.15
    acles
    0.14
    POSITIVE LOGITS
    ر
    0.19
    جي
    0.17
    יי
    0.17
    يرة
    0.17
    ר
    0.17
    <unused1146>
    0.17
    SCO
    0.16
    ECH
    0.16
    尘
    0.16
    μη
    0.16
    Activations Density 0.007%

    No Known Activations