© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88230
    Prev
    Next
    INDEX
    Explanations

    Mitch Hedberg or matching sentences

    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
     match
    0.93
    <0x0D>
    0.81
     are
    0.76
    </b>
    0.75
     matched
    0.74
    um
    0.74
    ک
    0.74
    </h2>
    0.73
    </h3>
    0.72
     matchmaking
    0.72
    POSITIVE LOGITS
    achev
    0.62
    ﻮ
    0.59
    midrule
    0.59
    郓
    0.58
    setcounter
    0.57
     hypothes
    0.57
    入手
    0.56
    чи
    0.56
    jší
    0.56
    例外
    0.56
    Activations Density 0.001%

    No Known Activations