© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153705
    Prev
    Next
    INDEX
    Explanations

    both [option 1] and [option 2]

    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_23_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
    從小
    0.39
    โน
    0.38
    ASS
    0.37
    Billboard
    0.35
    უკ
    0.35
    gitlab
    0.34
    🅽
    0.33
    ーン
    0.33
    unam
    0.33
    禰
    0.33
    POSITIVE LOGITS
     jammed
    0.42
     β
    0.40
     bords
    0.39
     RetValue
    0.39
     inflam
    0.38
     জেনে
    0.38
     α
    0.38
     火
    0.38
     blobs
    0.38
     τ
    0.38
    Activations Density 0.004%

    No Known Activations