© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6522
    Prev
    Next
    INDEX
    Explanations

    tailored suggestions

    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
    er
    2.34
    र
    1.84
    is
    1.57
    ার
    1.46
     tiempos
    1.41
    erent
    1.38
    વાહી
    1.29
    گاہ
    1.29
    erler
    1.29
    vskip
    1.28
    POSITIVE LOGITS
    ب
    1.96
    𝚘
    1.58
    స్
    1.49
    sided
    1.43
    ition
    1.40
     shouldUse
    1.36
    Ր
    1.35
    𝚛
    1.35
    ISTRATION
    1.33
    थुरा
    1.32
    Activations Density 0.009%

    No Known Activations