© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203377
    Prev
    Next
    INDEX
    Explanations

    abre

    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_6_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
     I
    1.14
     whiteboard
    1.08
     B
    1.02
    at
    1.01
     pronoun
    0.98
    :
    0.97
     progression
    0.96
     mutation
    0.96
     high
    0.96
     F
    0.95
    POSITIVE LOGITS
    ಮ
    1.16
    كان
    1.13
    ли
    1.05
    ак
    1.05
    الس
    1.04
    அ
    1.04
    یک
    1.02
    અ
    1.01
    ان
    0.98
    ন
    0.97
    Activations Density 0.001%

    No Known Activations