© 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. 7868
    Prev
    Next
    INDEX
    Explanations

    seriously followed by punctuation

    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
     synonymous
    3.05
    儡
    2.70
    یل
    2.69
    plasia
    2.56
     علا
    2.36
    енты
    2.31
     annoying
    2.30
     Categor
    2.28
     Aidan
    2.28
    서
    2.26
    POSITIVE LOGITS
    ፍተኛ
    2.51
    ுள்ளார்
    2.47
    FT
    2.35
    awaited
    2.33
    idade
    2.24
    CAG
    2.16
    య
    2.12
     retractable
    2.12
    yloxy
    2.11
    Come
    2.11
    Activations Density 0.085%

    No Known Activations