© 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. 9646
    Prev
    Next
    INDEX
    Explanations

    emotions

    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
    fehl
    0.64
    pmatrix
    0.64
     綿
    0.63
    防火
    0.63
    ዋ
    0.62
    jecha
    0.61
    ensin
    0.59
    嗪
    0.59
    ാര്യ
    0.59
    ospod
    0.59
    POSITIVE LOGITS
     frustration
    2.91
     disappointment
    2.70
     disappointed
    2.69
     dismay
    2.59
     sadness
    2.48
     frustrated
    2.45
     anger
    2.43
     thrilled
    2.40
     excitement
    2.34
     anxiety
    2.32
    Activations Density 0.465%

    No Known Activations