© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6147
    Prev
    Next
    INDEX
    Explanations

    Pixel 8 Pro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ed
    2.36
    ة
    2.29
     GameOver
    2.18
     maxY
    2.12
     cercano
    2.08
    ך
    2.08
    Қ
    2.05
    ัย
    2.05
     встре
    2.02
     lintas
    2.00
    POSITIVE LOGITS
    ра
    2.83
    σ
    2.41
    larda
    2.41
    рни
    2.35
    ু
    2.32
    weg
    2.31
    kec
    2.27
    m
    2.25
     tachycardia
    2.22
    \|\
    2.18
    Activations Density 0.002%

    No Known Activations