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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9186
    Prev
    Next
    INDEX
    Explanations

    wikipedia lists

    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
     {{
    1.41
    {{
    1.25
     Template
    1.25
    Template
    1.24
    templates
    1.08
    ">{{
    1.05
     templates
    1.04
    >{{
    1.02
     {{{
    1.02
    Templates
    1.01
    POSITIVE LOGITS
     entertained
    0.72
     แนะ
    0.71
     Elite
    0.70
     mesmer
    0.69
    ."-
    0.68
     الالكتروني
    0.67
    ＰＥ
    0.66
    textrm
    0.66
    呪
    0.65
    asma
    0.63
    Activations Density 0.014%

    No Known Activations