© 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. 8776
    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
    ১
    2.68
    การ
    2.39
    ير
    2.30
    тся
    2.26
    情況
    2.18
    perature
    2.14
     Ges
    2.13
    Karnataka
    2.08
    сто
    2.07
    いて
    2.06
    POSITIVE LOGITS
    ا
    3.50
    я
    3.34
    ה
    2.88
     sở
    2.59
    ፍተኛ
    2.31
    ائل
    2.26
     impressive
    2.25
     Amended
    2.23
    afe
    2.20
    /=
    2.19
    Activations Density 0.025%

    No Known Activations