© 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. 86672
    Prev
    Next
    INDEX
    Explanations

    potential benefits, risks, questions

    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
    </h2>
    0.80
    <0x0D>
    0.72
    ↵
    0.59
    ons
    0.57
    </b>
    0.55
    </h1>
    0.54
     idiosyncratic
    0.53
    ться
    0.53
    jęcia
    0.52
    </td>
    0.51
    POSITIVE LOGITS
    _
    0.80
    大
    0.78
    一
    0.72
    d
    0.72
    ت
    0.66
    ה
    0.66
    p
    0.65
    ствия
    0.61
    המ
    0.61
    ول
    0.59
    Activations Density 0.004%

    No Known Activations