© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138953
    Prev
    Next
    INDEX
    Explanations

    direction

    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_37_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
    DOWN
    0.44
    potato
    0.40
    ≾
    0.38
     potato
    0.37
    Potato
    0.37
    Down
    0.36
    (&
    0.35
    DeviceId
    0.35
    ꧂
    0.35
     अंक
    0.35
    POSITIVE LOGITS
    嗚
    0.38
    +(\
    0.38
     advanced
    0.37
     checkboxes
    0.37
     soie
    0.36
    ẫ
    0.36
     scar
    0.35
     Lola
    0.35
     सोर्स
    0.35
     slaughtered
    0.34
    Activations Density 0.006%

    No Known Activations