© 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. 204566
    Prev
    Next
    INDEX
    Explanations

    burst out laughing

    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
     hospitality
    0.44
     Hospitality
    0.41
     breasts
    0.40
     fight
    0.40
     hormonal
    0.40
     physico
    0.40
     Juno
    0.39
    ►
    0.39
     taste
    0.38
     hectic
    0.37
    POSITIVE LOGITS
     записа
    0.38
    ható
    0.36
     awarded
    0.36
     ace
    0.35
    greencar
    0.35
    Forum
    0.34
     싶은
    0.34
    TIA
    0.34
     implicitly
    0.33
     সত্যা
    0.33
    Activations Density 0.001%

    No Known Activations