© 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. 61121
    Prev
    Next
    INDEX
    Explanations

    Chapel Hill, Aachen, Arielle

    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
    il
    1.40
    ться
    1.40
    x
    1.06
    ל
    1.06
    ᓘ
    1.00
    ig
    0.99
     osobow
    0.94
     рассказа
    0.93
    ec
    0.92
    atak
    0.92
    POSITIVE LOGITS
    ش
    1.51
    </h2>
    1.45
    기
    1.45
    </h1>
    1.42
    </h3>
    1.38
     to
    1.34
    IS
    1.31
    أ
    1.26
    </h6>
    1.25
    </h4>
    1.24
    Activations Density 0.001%

    No Known Activations