© 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. 7296
    Prev
    Next
    INDEX
    Explanations

    quantity or count

    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
    து
    1.33
    liance
    1.25
    tr
    1.24
    𝗻
    1.21
    چه
    1.19
    อร์
    1.18
     hora
    1.17
     flott
    1.12
    ռ
    1.12
    کھ
    1.12
    POSITIVE LOGITS
    ев
    1.61
    ت
    1.57
     flanking
    1.42
     Consecutive
    1.40
    en
    1.37
    𝒅
    1.37
    kannya
    1.36
     које
    1.34
    jų
    1.34
    Checked
    1.31
    Activations Density 0.035%

    No Known Activations