© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3248
    Prev
    Next
    INDEX
    Explanations

    globally or worldwide

    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_5_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
    вали
    1.33
    ка
    1.28
     بالم
    1.25
    데
    1.21
    де
    1.17
     PublicKey
    1.11
    kv
    1.11
    ன்
    1.08
     стане
    1.08
    ல்
    1.08
    POSITIVE LOGITS
     parseFloat
    1.26
     catalysis
    1.17
     omitted
    1.15
     magnetores
    1.15
    ushal
    1.14
     sinn
    1.13
     postdoctoral
    1.13
    笆
    1.12
    }.
    1.11
     möj
    1.11
    Activations Density 0.007%

    No Known Activations