© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42842
    Prev
    Next
    INDEX
    Explanations

    primary way, reason, function, center, organ, site

    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_22_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
    concatenate
    0.36
    ೋ
    0.36
    imetry
    0.36
    winged
    0.36
     পদ
    0.34
    ängt
    0.34
     bijective
    0.33
     contractions
    0.32
    更好地
    0.32
    dal
    0.32
    POSITIVE LOGITS
     miei
    0.37
     mW
    0.37
    ﺙ
    0.36
    ില
    0.35
    ᴱ
    0.35
     casually
    0.35
     GSi
    0.35
    <unused58>
    0.34
     Bxa
    0.34
     Sierra
    0.34
    Activations Density 0.018%

    No Known Activations