© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202197
    Prev
    Next
    INDEX
    Explanations

    cognitive linguistics and conceptual metaphors

    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
     পার্থ
    0.41
    schnitt
    0.37
     процессо
    0.37
    Aur
    0.36
     Bure
    0.36
    准
    0.36
    Anime
    0.36
    準
    0.36
    Rect
    0.36
     Quan
    0.35
    POSITIVE LOGITS
     Lak
    0.66
     conceptual
    0.66
    Conceptual
    0.64
     Conceptual
    0.64
    conceptual
    0.61
     metaphor
    0.58
     metaphors
    0.55
    Lak
    0.53
     cognitive
    0.50
     Cognitive
    0.50
    Activations Density 0.002%

    No Known Activations