© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46055
    Prev
    Next
    INDEX
    Explanations

    through the

    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_13_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
    trashItem
    0.53
     empath
    0.52
     curto
    0.51
     aligns
    0.50
     Idani
    0.48
    ✞
    0.48
     untouch
    0.47
     contradictions
    0.47
     demean
    0.46
    AssignableFrom
    0.46
    POSITIVE LOGITS
    h
    0.79
    an
    0.72
    its
    0.59
    as
    0.55
    ide
    0.55
    in
    0.53
    ur
    0.53
    res
    0.53
    lo
    0.53
    quiry
    0.52
    Activations Density 0.020%

    No Known Activations