© 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. 210965
    Prev
    Next
    INDEX
    Explanations

    summarize thesis points

    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
    Tr
    0.42
    Scoped
    0.41
    Flat
    0.40
    Lad
    0.39
     r
    0.38
    Implement
    0.38
     Residency
    0.38
    Staying
    0.38
     résidence
    0.37
    방법
    0.37
    POSITIVE LOGITS
     chromatic
    0.47
     weaknesses
    0.46
     compromet
    0.45
     nuanced
    0.44
     comprom
    0.43
     vulnerabilities
    0.43
     კომპ
    0.43
    hdd
    0.43
    猞
    0.43
     krom
    0.42
    Activations Density 0.002%

    No Known Activations