© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163031
    Prev
    Next
    INDEX
    Explanations

    ways things fall

    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_31_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
     relocated
    0.55
     relocation
    0.54
     relocate
    0.53
    遷
    0.50
     move
    0.48
     reloc
    0.48
    迁
    0.47
     relocating
    0.47
     moved
    0.39
    Move
    0.39
    POSITIVE LOGITS
     trich
    0.34
     StandardScaler
    0.34
    figcaption
    0.33
    ডা
    0.33
     pairwise
    0.32
    嚎
    0.32
    jols
    0.32
     APPROACH
    0.31
     centrifugation
    0.31
     લાવ
    0.31
    Activations Density 0.017%

    No Known Activations