© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3397
    Prev
    Next
    INDEX
    Explanations

    NOT detected or followed by what's true

    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_5_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
    {}".
    0.63
    𝕤
    0.61
     dlatego
    0.60
    
    0.57
    {}'.
    0.57
    .|__
    0.57
    <%=
    0.56
    ಛ
    0.55
    ))/
    0.54
    েনারেল
    0.53
    POSITIVE LOGITS
    もっと
    0.62
    и
    0.60
    ни
    0.59
    ी
    0.59
     poss
    0.58
    in
    0.55
    }
    0.53
    hbox
    0.51
    ী
    0.49
    на
    0.49
    Activations Density 0.036%

    No Known Activations