© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 25791
    Prev
    Next
    INDEX
    Explanations

    Executive Summary

    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_10_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
    ي
    0.26
    i
    0.25
    ين
    0.24
    il
    0.22
    on
    0.21
    osť
    0.21
    Params
    0.21
    ués
    0.21
    u
    0.21
    <unused24>
    0.20
    POSITIVE LOGITS
    </h4>
    0.28
    },
    0.24
    }
    0.24
    </h2>
    0.23
    </h3>
    0.22
    }/>
    0.22
    </h1>
    0.21
    </strong>
    0.21
    ).
    0.20
    }$
    0.19
    Activations Density 0.063%

    No Known Activations