© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8260
    Prev
    Next
    INDEX
    Explanations

    responding to

    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
    ...+
    0.80
     kommt
    0.66
    lact
    0.65
     participle
    0.64
     dealing
    0.63
     гуляць
    0.63
     comprend
    0.63
     Başkan
    0.62
     што
    0.60
    šnje
    0.60
    POSITIVE LOGITS
    ת
    0.76
    אים
    0.72
    ло
    0.70
    ка
    0.64
    ably
    0.63
    সুতরাং
    0.62
     fois
    0.59
    eba
    0.59
    те
    0.59
    ામ
    0.59
    Activations Density 0.111%

    No Known Activations