© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61656
    Prev
    Next
    INDEX
    Explanations

    aliens

    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_59_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
    α
    0.67
     Alpha
    0.61
    Alpha
    0.59
     alpha
    0.54
     α
    0.54
    alpha
    0.53
    ia
    0.50
    క
    0.49
    ie
    0.48
     ALPHA
    0.47
    POSITIVE LOGITS
    xl
    0.46
    aaa
    0.45
    hardhat
    0.45
    fac
    0.42
    拔
    0.41
    j
    0.41
    aa
    0.40
    xg
    0.40
    cg
    0.40
    bí
    0.40
    Activations Density 0.003%

    No Known Activations