© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6204
    Prev
    Next
    INDEX
    Explanations

    speed and pitch adjustment

    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_39_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
    寫
    0.51
     écrit
    0.46
     escreveu
    0.43
    写
    0.41
    書き
    0.40
     تكتب
    0.40
     écrire
    0.40
     لکھ
    0.39
    เขียน
    0.38
    编写
    0.38
    POSITIVE LOGITS
     pequenos
    0.38
     speed
    0.37
     pequeno
    0.37
    âm
    0.36
    )_{
    0.36
    ামো
    0.35
     revolutions
    0.35
    ങ്ങളെ
    0.35
    asını
    0.34
    rub
    0.34
    Activations Density 0.002%

    No Known Activations