© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2939
    Prev
    Next
    INDEX
    Explanations

    "hyp" words

    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_44_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
    淞
    0.40
     Dele
    0.39
    蝠
    0.38
     سلم
    0.37
    洒落
    0.36
    वरी
    0.36
    諡
    0.36
    utral
    0.35
    ెం
    0.35
    松
    0.35
    POSITIVE LOGITS
     Hyp
    2.75
    Hyp
    2.72
    hyp
    2.67
     hyp
    2.55
     hypo
    2.45
     hypot
    2.03
     Hypot
    1.83
     hypoc
    1.75
     hypoth
    1.74
     hypoallergenic
    1.69
    Activations Density 0.116%

    No Known Activations