© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214790
    Prev
    Next
    INDEX
    Explanations

    whole

    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_47_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
     whole
    0.59
    whole
    0.56
     hele
    0.52
     keseluruhan
    0.47
    Whole
    0.46
     ganze
    0.44
     Whole
    0.43
    ".*:
    0.43
     ganzen
    0.43
     egész
    0.42
    POSITIVE LOGITS
    менование
    0.41
    aying
    0.40
    angement
    0.38
    きたい
    0.38
     przys
    0.38
     hitch
    0.37
     répon
    0.36
    番
    0.35
     armed
    0.35
    نید
    0.34
    Activations Density 0.002%

    No Known Activations