© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210818
    Prev
    Next
    INDEX
    Explanations

    known as

    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_5_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
     that
    1.46
    </h3>
    1.27
    ו
    1.24
    ным
    1.23
    '
    1.16
    ure
    1.13
    .
    1.13
    that
    1.10
    IL
    1.08
    ها
    1.07
    POSITIVE LOGITS
    ون
    1.19
    ем
    1.15
    h
    1.14
    }$.
    1.11
    have
    1.10
    り
    1.06
    يد
    1.02
    }
    0.99
    ل
    0.99
    ství
    0.96
    Activations Density 0.000%

    No Known Activations