© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4680
    Prev
    Next
    INDEX
    Explanations

    savings account

    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
    р
    0.75
    a
    0.74
    犸
    0.68
     eer
    0.63
     reconciled
    0.62
    ように
    0.62
     unbedingt
    0.61
    П
    0.61
    ρ
    0.61
     hark
    0.60
    POSITIVE LOGITS
     cmap
    0.99
    瀣
    0.92
    ுமா
    0.89
     pdb
    0.87
     doings
    0.83
    simplify
    0.82
    ութ
    0.81
    Roxy
    0.81
    얇
    0.81
    ে
    0.80
    Activations Density 0.009%

    No Known Activations