© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 152909
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    ０
    0.56
    <0x80>
    0.48
    ០
    0.44
    0
    0.43
    ૦
    0.40
     ০
    0.39
    𝟎
    0.39
    ٠
    0.38
     ০১
    0.38
    ⓪
    0.35
    POSITIVE LOGITS
    3
    1.22
    2
    1.18
    7
    1.18
    4
    1.16
    6
    1.14
    9
    1.09
    8
    1.08
    5
    1.05
    1
    0.98
    ۳
    0.70
    Activations Density 0.056%

    No Known Activations