© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9428
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    ᱗
    0.76
    सिव
    0.67
    アクセス
    0.67
     reaching
    0.66
    ৩
    0.64
     アクセ
    0.64
     सात
    0.64
    䖝
    0.64
    ৪
    0.63
     ради
    0.62
    POSITIVE LOGITS
    xx
    0.91
    XX
    0.89
    ००
    0.76
    oo
    0.72
     XXV
    0.68
     XX
    0.67
    uban
    0.67
     OO
    0.67
     YY
    0.66
     XXII
    0.66
    Activations Density 0.080%

    No Known Activations