© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65704
    Prev
    Next
    INDEX
    Explanations

    vowel and consonant sounds

    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_41_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
     உற்ப
    0.39
    澥
    0.37
    alba
    0.36
     Attribution
    0.34
    \}-
    0.34
    प्रति
    0.34
    گنڈ
    0.34
     kc
    0.34
    ☇
    0.34
     साठी
    0.33
    POSITIVE LOGITS
     vowel
    1.72
     vowels
    1.71
     consonant
    1.49
     consonants
    1.45
     conson
    1.23
     Cons
    1.20
    Cons
    1.16
     kons
    1.10
     cons
    1.00
     samoglas
    1.00
    Activations Density 0.008%

    No Known Activations