© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58212
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Så
    0.41
    ﻪ
    0.38
     博文
    0.37
     ],"
    0.37
    Witam
    0.36
    которы
    0.36
    María
    0.34
    så
    0.33
     EF
    0.33
    </iframe>
    0.33
    POSITIVE LOGITS
    .
    0.56
    ،
    0.53
     this
    0.46
    ,
    0.46
     can
    0.45
     could
    0.45
     wasn
    0.44
    ,​
    0.42
    ፣
    0.42
     should
    0.40
    Activations Density 0.015%

    No Known Activations