© 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. 153253
    Prev
    Next
    INDEX
    Explanations

    prevailing

    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
     gasp
    0.39
    の発
    0.38
     slimming
    0.38
     nhưng
    0.38
     활용
    0.38
     трав
    0.37
     весе
    0.37
    咋
    0.37
     continuing
    0.36
     disposiciones
    0.36
    POSITIVE LOGITS
     half
    0.65
    half
    0.62
    Half
    0.60
     Half
    0.58
    ifornia
    0.49
     HALF
    0.47
    HALF
    0.44
    olin
    0.44
    illion
    0.43
    adion
    0.43
    Activations Density 0.000%

    No Known Activations