© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14179
    Prev
    Next
    INDEX
    Explanations

    adding something new

    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_15_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
    </h4>
    0.23
    ৪
    0.22
    طار
    0.22
    MIX
    0.21
    ב
    0.21
    gbar
    0.21
    الن
    0.21
    점
    0.21
    Spectral
    0.21
    ۸
    0.21
    POSITIVE LOGITS
     procured
    0.21
     चाहिए
    0.20
     мы
    0.19
    anoate
    0.19
     priest
    0.19
     habitants
    0.19
     сможете
    0.19
     पकड़
    0.19
     formalized
    0.19
    ется
    0.19
    Activations Density 0.051%

    No Known Activations