© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108277
    Prev
    Next
    INDEX
    Explanations

    offer

    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_2_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
    daki
    1.20
    et
    1.18
    us
    1.16
    ed
    1.13
    و
    1.06
    il
    1.05
    a
    1.05
    al
    1.05
    وپ
    1.02
    eg
    1.00
    POSITIVE LOGITS
    </h2>
    1.79
    <0x0D>
    1.64
    </h3>
    1.46
    </h4>
    1.43
    </h1>
    1.39
    </h6>
    1.37
    </b>
    1.30
    </h5>
    1.28
    </strong>
    1.27
    </u>
    1.21
    Activations Density 0.000%

    No Known Activations