© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116580
    Prev
    Next
    INDEX
    Explanations

    CVE identifier and details

    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_27_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
    संस्करण
    0.41
    מור
    0.40
    __*/
    0.38
    स्त्रा
    0.36
    कल
    0.36
    大量的
    0.36
    следование
    0.36
    αι
    0.35
    ཌ
    0.35
    يميديا
    0.34
    POSITIVE LOGITS
     ihtiy
    0.42
     taxonom
    0.42
     equate
    0.41
     taxonomy
    0.41
     need
    0.40
    ectl
    0.40
     etk
    0.39
     Taxonomy
    0.39
     Medicina
    0.38
     primed
    0.37
    Activations Density 0.001%

    No Known Activations