© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9710
    Prev
    Next
    INDEX
    Explanations

    structured data references

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     entertained
    0.72
     الالكتروني
    0.72
     mesmer
    0.71
     แนะ
    0.70
    ̧
    0.65
    ."-
    0.65
     mesmerizing
    0.65
     excitedly
    0.64
    ̉
    0.63
    李
    0.63
    POSITIVE LOGITS
     {{
    1.48
     Template
    1.42
    Template
    1.35
    {{
    1.32
     templates
    1.18
     template
    1.15
    templates
    1.13
    Templates
    1.12
     {{{
    1.11
     Templates
    1.11
    Activations Density 0.170%

    No Known Activations