© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51382
    Prev
    Next
    INDEX
    Explanations

    have

    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_55_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
    StringEncoding
    0.40
    可通过
    0.38
    តាម
    0.37
    संख्यक
    0.36
    WHIT
    0.36
     Où
    0.35
    मारक
    0.35
    舂
    0.35
    Tenn
    0.34
    ↕
    0.34
    POSITIVE LOGITS
     bad
    0.51
     like
    0.48
     anxiety
    0.47
     depression
    0.46
     trauma
    0.46
     dementia
    0.45
     sickness
    0.44
     insomnia
    0.43
     Anxiety
    0.43
     didnt
    0.43
    Activations Density 0.009%

    No Known Activations