© 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. 3140
    Prev
    Next
    INDEX
    Explanations

    pros and cons or no

    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
    ку
    0.70
    здат
    0.61
     Caedwalla
    0.58
    ᴍ
    0.57
     exertions
    0.56
    র্দ
    0.55
     billionaires
    0.54
     extol
    0.54
     physic
    0.53
    лас
    0.53
    POSITIVE LOGITS
    '/
    0.62
    boolean
    0.60
    ી
    0.56
    means
    0.54
    }$.
    0.54
    }$,
    0.54
    nh
    0.53
    puma
    0.53
    nt
    0.52
    |</
    0.52
    Activations Density 0.365%

    No Known Activations