© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    names

    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_5_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
     која
    0.85
     основ
    0.76
    nosti
    0.75
    sliced
    0.75
    slice
    0.71
     stessa
    0.71
     कुमारी
    0.67
    탭
    0.66
    synchronized
    0.66
     Fatima
    0.66
    POSITIVE LOGITS
     salido
    0.74
    וח
    0.73
    Ũ
    0.71
    ilio
    0.71
    ্দ
    0.70
    ודי
    0.70
    ભાઈ
    0.70
    IDENTIAL
    0.69
    ito
    0.69
    hadas
    0.69
    Activations Density 0.088%

    No Known Activations