© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154666
    Prev
    Next
    INDEX
    Explanations

    variable

    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
    Kaynakça
    0.43
    ⵡ
    0.41
    Wet
    0.40
     aproximadamente
    0.39
    零售
    0.39
     unhappiness
    0.39
    ティック
    0.38
     علیکم
    0.38
    ި
    0.38
    言葉
    0.37
    POSITIVE LOGITS
    variable
    0.72
     variable
    0.57
    vertical
    0.55
    compatible
    0.55
    visible
    0.53
     compatible
    0.53
    progressive
    0.52
    resonant
    0.52
    readable
    0.49
    dependent
    0.49
    Activations Density 0.002%

    No Known Activations