© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205467
    Prev
    Next
    INDEX
    Explanations

    obviously, totally, definitely

    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
    叧
    0.44
     بالفعل
    0.41
    अधिकांश
    0.40
     എന്നാൽ
    0.39
     دیده
    0.37
    셰
    0.37
    rello
    0.36
    鲸
    0.36
    ác
    0.36
    apods
    0.35
    POSITIVE LOGITS
     طبعا
    0.63
    (!)
    0.63
     obviously
    0.61
     totally
    0.60
     (!)
    0.59
    Obviously
    0.58
     definitely
    0.57
     Obviously
    0.57
    Definitely
    0.55
    totally
    0.55
    Activations Density 0.004%

    No Known Activations