© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236622
    Prev
    Next
    INDEX
    Explanations

    olds

    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_32_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
    勵
    0.40
    ','"+
    0.40
    洗
    0.39
    Tomorrow
    0.37
    決勝
    0.37
    lick
    0.37
    lisi
    0.37
    训
    0.37
    wash
    0.36
    lysninger
    0.36
    POSITIVE LOGITS
     detections
    0.44
     Sicherheit
    0.40
     STRU
    0.40
     security
    0.38
     contamination
    0.37
     infar
    0.37
     cofactor
    0.36
     tumors
    0.36
     deformity
    0.36
     residual
    0.36
    Activations Density 0.006%

    No Known Activations