© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170964
    Prev
    Next
    INDEX
    Explanations

    part of me

    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_20_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
     whaling
    0.30
     Smile
    0.29
     mewah
    0.29
     vượt
    0.29
    महल
    0.29
     gioi
    0.29
    <0x8F>
    0.28
     chewy
    0.28
     sparsely
    0.28
     fiasco
    0.28
    POSITIVE LOGITS
    &
    0.31
    विष्ट
    0.27
    ELL
    0.25
    ;\;\
    0.25
    ellä
    0.25
    ­
    0.25
    Platform
    0.24
    bootstrapcdn
    0.24
    EL
    0.24
    ков
    0.24
    Activations Density 0.003%

    No Known Activations