© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34973
    Prev
    Next
    INDEX
    Explanations

    speaking voice

    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
     zéro
    0.43
    zero
    0.42
    Zero
    0.41
    誤差
    0.40
     зарегистри
    0.40
     статисти
    0.39
    測定
    0.39
    赉
    0.39
    纲
    0.39
     भर
    0.38
    POSITIVE LOGITS
     voice
    0.46
     voix
    0.41
    voice
    0.38
    เสียง
    0.37
     voices
    0.36
     lcm
    0.36
     صوت
    0.35
    声音
    0.35
    的声音
    0.35
     அறிவு
    0.35
    Activations Density 0.018%

    No Known Activations