© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195636
    Prev
    Next
    INDEX
    Explanations

    Now, a new situation

    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_27_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
     belongs
    0.35
     belong
    0.32
     WEL
    0.31
     underlies
    0.31
    馋
    0.31
    igeons
    0.31
     alleges
    0.30
     वेजिट
    0.30
     ISSN
    0.30
     relies
    0.30
    POSITIVE LOGITS
     പ്രത്യേക
    0.33
    েল
    0.30
     যোগ্যতা
    0.30
     imali
    0.30
    ։
    0.29
     اشاره
    0.29
    ForRule
    0.28
    jści
    0.28
    𝗋
    0.27
    circular
    0.27
    Activations Density 0.001%

    No Known Activations