© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1389
    Prev
    Next
    INDEX
    Explanations

    Abraham Saracco founder

    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_39_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
     ११
    0.42
    turbulence
    0.36
     ९
    0.35
     ۹
    0.35
     शि
    0.35
    Saudi
    0.34
    姏
    0.33
     வல்ல
    0.33
    ୯
    0.33
    ल्याण
    0.32
    POSITIVE LOGITS
     --
    0.35
     Pattes
    0.34
    Formation
    0.33
    unj
    0.32
     proof
    0.32
    τος
    0.32
     Formation
    0.32
    ۣ
    0.31
    ioned
    0.31
     homage
    0.31
    Activations Density 0.011%

    No Known Activations