© 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. 6768
    Prev
    Next
    INDEX
    Explanations

    sound effects like lush pads and ambient

    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
     Resp
    0.37
    setCode
    0.37
     Pointer
    0.36
    Samantha
    0.36
     Samantha
    0.35
    Codes
    0.35
    様
    0.35
     Codes
    0.34
    BOUNDARY
    0.33
    횟
    0.33
    POSITIVE LOGITS
     synthesis
    0.50
     gain
    0.47
     delayed
    0.46
    Gain
    0.44
     busses
    0.42
    gain
    0.42
     subtract
    0.41
    GAIN
    0.41
     delays
    0.40
     buses
    0.40
    Activations Density 0.180%

    No Known Activations