© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148811
    Prev
    Next
    INDEX
    Explanations

    Talmud, psy, eosin, Re:zero, DL, Search

    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_18_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
    ber
    0.49
     parallax
    0.46
    z
    0.46
     Ber
    0.45
    }=(
    0.45
     E
    0.45
     sandwich
    0.45
     quarter
    0.44
     z
    0.44
     parabola
    0.44
    POSITIVE LOGITS
    𝘯
    0.57
    蜕
    0.50
    개발
    0.50
    <0x8C>
    0.49
    𝗱
    0.49
    ലോക
    0.48
    𝘨
    0.47
    gradients
    0.47
     proliferating
    0.47
    నుంది
    0.47
    Activations Density 0.000%

    No Known Activations