© 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. 49725
    Prev
    Next
    INDEX
    Explanations

    speaking animals

    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
     propio
    0.40
     рынок
    0.38
    ٹنگ
    0.36
    ㈤
    0.36
    LastGen
    0.35
     také
    0.35
     gesprochen
    0.35
     shoved
    0.34
    orgement
    0.34
    鸫
    0.34
    POSITIVE LOGITS
    dist
    0.33
    还可以
    0.31
     wits
    0.31
     cu
    0.30
    bit
    0.30
    id
    0.29
    end
    0.29
    mui
    0.29
    celle
    0.29
     '
    0.29
    Activations Density 0.237%

    No Known Activations