© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152379
    Prev
    Next
    INDEX
    Explanations

    adds flavor

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     S
    0.81
     الس
    0.59
    S
    0.54
    𝑺
    0.43
    setVisibility
    0.42
     Foods
    0.42
    ("/")
    0.42
     Users
    0.41
    𝚂
    0.41
     Maturity
    0.41
    POSITIVE LOGITS
     body
    0.98
    body
    0.86
    Body
    0.77
     cuerpo
    0.76
     relish
    0.75
     savor
    0.75
     Body
    0.74
     bodies
    0.73
     몸
    0.72
     BODY
    0.71
    Activations Density 0.005%

    No Known Activations