© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127200
    Prev
    Next
    INDEX
    Explanations

    there once was a

    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_3_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
    ure
    0.68
    fa
    0.61
    𝗳
    0.59
    اکہ
    0.58
    crossentropy
    0.58
    cou
    0.57
    është
    0.57
    dokter
    0.57
    uman
    0.57
    te
    0.56
    POSITIVE LOGITS
    <0x0D>
    1.05
    </h3>
    0.98
    ه
    0.87
    </b>
    0.80
    ي
    0.80
    ا
    0.79
    </i>
    0.78
    ה
    0.77
    ט
    0.75
    '
    0.71
    Activations Density 0.001%

    No Known Activations