© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77953
    Prev
    Next
    INDEX
    Explanations

    even if

    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_31_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
     kehilangan
    0.39
    itated
    0.38
     |”
    0.37
     precludes
    0.37
    Map
    0.36
    缺失
    0.36
    ToIndex
    0.36
    失去
    0.35
    टेज
    0.35
    ಓ
    0.35
    POSITIVE LOGITS
     part
    0.39
     saturated
    0.37
    짠
    0.37
     purposeful
    0.37
     acompa
    0.36
     minimally
    0.36
     mysticism
    0.36
     myst
    0.35
     parts
    0.35
     proposition
    0.35
    Activations Density 0.005%

    No Known Activations