© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147174
    Prev
    Next
    INDEX
    Explanations

    `

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    iled
    0.40
     હતો
    0.38
     হয়েছিল
    0.37
     wi
    0.34
    越し
    0.34
     ছিলো
    0.34
    کھوں
    0.34
    又
    0.33
    द्धि
    0.33
    валось
    0.33
    POSITIVE LOGITS
     Into
    0.47
     !”
    0.45
    .”
    0.44
     obviously
    0.44
     MAR
    0.43
    marin
    0.43
    .»
    0.42
     Accordingly
    0.42
     path
    0.42
    .“
    0.42
    Activations Density 0.004%

    No Known Activations