© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79055
    Prev
    Next
    INDEX
    Explanations

    holy grail

    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_0_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
    ر
    1.83
    ва
    1.70
    л
    1.65
    ло
    1.63
    ل
    1.58
    r
    1.57
    ig
    1.41
    berly
    1.38
    an
    1.36
    il
    1.31
    POSITIVE LOGITS
    ի
    1.35
    ).
    1.34
     ۳
    1.28
    は
    1.23
    の
    1.20
     ३
    1.14
    ‌ی
    1.12
    의
    1.12
     ferv
    1.09
    </th>
    1.08
    Activations Density 0.001%

    No Known Activations