© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110957
    Prev
    Next
    INDEX
    Explanations

    dubious

    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_2_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
    2
    1.26
    ामध्ये
    1.20
    v
    1.10
    ä
    1.08
    िर
    1.04
    iel
    1.02
    c
    1.02
    ای
    1.01
    3
    1.00
    ഴിഞ്ഞ
    0.99
    POSITIVE LOGITS
    י
    1.31
    ０
    1.28
    सँग
    1.21
     as
    1.13
    li
    1.13
     comforted
    1.13
    ०
    1.11
    𝟎
    1.11
    ᱐
    1.08
    ட்சத்திர
    1.07
    Activations Density 0.000%

    No Known Activations