© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9325
    Prev
    Next
    INDEX
    Explanations

    SpongeBob

    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
    uições
    0.84
    丕
    0.83
    рос
    0.83
     perceber
    0.82
     petal
    0.80
     decisões
    0.78
     reconhecimento
    0.76
     guiclass
    0.75
    桃
    0.75
     معاہد
    0.74
    POSITIVE LOGITS
    Bob
    0.72
    hagen
    0.61
     sp
    0.61
    dress
    0.61
     Bob
    0.60
     esp
    0.58
    য়ন
    0.58
    ina
    0.57
    Dress
    0.56
     पा
    0.56
    Activations Density 0.002%

    No Known Activations