© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6880
    Prev
    Next
    INDEX
    Explanations

    laying down or lying

    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
    increment
    1.83
    ר
    1.80
     ziua
    1.75
    Investigators
    1.58
    да
    1.58
    𝐘
    1.56
    𝐄
    1.52
     belangrijke
    1.50
    ု
    1.49
    ρες
    1.49
    POSITIVE LOGITS
     dormant
    1.88
    ncol
    1.86
     основе
    1.76
    utenants
    1.74
    ный
    1.63
    ко
    1.61
    ные
    1.60
    鳅
    1.59
    тельств
    1.56
     Diffraction
    1.56
    Activations Density 0.053%

    No Known Activations