© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214915
    Prev
    Next
    INDEX
    Explanations

    named entities

    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_47_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
     certains
    0.45
     Certain
    0.44
     certain
    0.43
     certaines
    0.43
     acert
    0.42
    嚀
    0.42
    Certain
    0.41
     certaine
    0.41
     OW
    0.40
    Take
    0.39
    POSITIVE LOGITS
    yto
    0.36
    NullException
    0.36
     pasado
    0.35
    の特徴
    0.35
     passen
    0.34
     کمر
    0.34
    䐪
    0.34
    স্য
    0.34
     विष्णु
    0.33
    एलबी
    0.33
    Activations Density 0.000%

    No Known Activations