© 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. 7758
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    siniz
    1.03
    ا
    1.03
    স্থানীয়
    0.98
     volc
    0.97
    𝙉
    0.94
    𝐸
    0.92
     rámci
    0.92
    ния
    0.92
    𝑌
    0.91
     foment
    0.91
    POSITIVE LOGITS
    ला
    1.13
    ne
    1.10
     choses
    1.00
    ist
    0.98
    नी
    0.97
    ound
    0.93
    ч
    0.93
    HING
    0.93
    כם
    0.91
    на
    0.90
    Activations Density 0.076%

    No Known Activations