Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 33-GEMMASCOPE-2-TRANSCODER-262K
    4. 261878
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_33_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
     pInBuffer
    0.79
    <unused354>
    0.78
    貨
    0.76
    ัญ
    0.76
    روں
    0.75
    Dijstra
    0.72
    ורך
    0.72
    держание
    0.72
    Lewis
    0.71
    𝐟
    0.71
    POSITIVE LOGITS
    }=-
    0.90
    mia
    0.89
    М
    0.87
    lt
    0.85
    hu
    0.85
     Zh
    0.84
    gt
    0.84
    Mm
    0.83
    cm
    0.83
    pn
    0.82
    Activations Density 0.000%

    No Known Activations