© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    conjunctions and progressions

    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
    Plus
    0.26
    Functions
    0.25
    Minus
    0.24
    PLUS
    0.23
    Without
    0.23
    Մ
    0.22
    Imports
    0.22
    썸
    0.22
    Appear
    0.21
    َال
    0.21
    POSITIVE LOGITS
     και
    0.31
     आणि
    0.28
     and
    0.28
     và
    0.26
     और
    0.26
     හා
    0.24
     మరియు
    0.24
     καὶ
    0.23
     və
    0.23
     и
    0.23
    Activations Density 0.184%

    No Known Activations