© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9429
    Prev
    Next
    INDEX
    Explanations

    G

    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
     rapat
    0.76
     Stich
    0.76
     Einsch
    0.76
     colère
    0.76
    
    0.74
     prije
    0.72
     airbag
    0.72
     handlerInput
    0.71
     absen
    0.71
     Antes
    0.70
    POSITIVE LOGITS
    Ú
    0.74
    UM
    0.71
    úp
    0.71
    тері
    0.64
    ROT
    0.60
    ást
    0.59
    Terminal
    0.58
    JPG
    0.56
    Ù
    0.56
    ודה
    0.55
    Activations Density 0.000%

    No Known Activations