© 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. 7455
    Prev
    Next
    INDEX
    Explanations

    xml root elements

    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
    তা
    1.35
    ت
    1.35
    
    1.13
     aikana
    1.10
     dealings
    1.09
    ेला
    1.09
     checkFor
    1.08
    redients
    1.06
    ை
    1.05
    లా
    1.04
    POSITIVE LOGITS
    mediate
    1.04
    م
    0.99
    क
    0.99
    면
    0.99
    finn
    0.98
    ...+
    0.97
    grass
    0.96
    سن
    0.94
     semidefinite
    0.93
    polished
    0.91
    Activations Density 0.004%

    No Known Activations