© 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. 8006
    Prev
    Next
    INDEX
    Explanations

    you and me

    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
    स्पद
    1.54
    การ
    1.40
    er
    1.39
    ্ড
    1.36
    𝐤
    1.35
    Informe
    1.33
     trifle
    1.33
    idée
    1.33
    تے
    1.32
    ından
    1.31
    POSITIVE LOGITS
    ی
    1.61
    ्या
    1.56
    ка
    1.48
    UM
    1.47
    𝙡
    1.44
    েই
    1.41
    Certainly
    1.40
    ाने
    1.36
     postulated
    1.34
    čku
    1.34
    Activations Density 0.183%

    No Known Activations