© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52572
    Prev
    Next
    INDEX
    Explanations

    github repository names

    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
    apura
    0.46
    plural
    0.38
    𒆪
    0.37
    धीरे
    0.36
    pura
    0.36
     ingat
    0.36
    Jogo
    0.36
    ujuan
    0.36
    maja
    0.36
     dinâmica
    0.36
    POSITIVE LOGITS
    这款
    0.44
    广
    0.39
     broad
    0.39
     mou
    0.38
     заслу
    0.38
     भाषण
    0.38
     deserved
    0.37
     sta
    0.37
     soles
    0.37
     mérite
    0.36
    Activations Density 0.001%

    No Known Activations