© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7489
    Prev
    Next
    INDEX
    Explanations

    IDA Pro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    これは
    1.76
    ли
    1.71
    𝐺
    1.59
    ються
    1.59
    𝐵
    1.56
    वर
    1.55
     voisines
    1.51
    दूर
    1.51
    know
    1.50
    ер
    1.47
    POSITIVE LOGITS
     dare
    1.59
    et
    1.56
    ﺢ
    1.55
     које
    1.47
    ̣c
    1.42
     গুলো
    1.41
     واح
    1.40
    (',');
    1.39
     beeswax
    1.38
     الشمس
    1.34
    Activations Density 0.001%

    No Known Activations