© 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. 45654
    Prev
    Next
    INDEX
    Explanations

    scopes or scope:

    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
     काही
    0.58
     Fluorescence
    0.52
     ایت
    0.51
     isotype
    0.50
     године
    0.49
     আইএস
    0.49
    祹
    0.49
    بعض
    0.49
    ᖓ
    0.49
    డుగు
    0.48
    POSITIVE LOGITS
    on
    0.53
    \
    0.51
     financial
    0.50
    ad
    0.44
     don
    0.42
     financier
    0.42
     financiero
    0.42
    шина
    0.41
     grip
    0.40
    ̣n
    0.40
    Activations Density 0.001%

    No Known Activations