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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4
    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_2_width_16k_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
    on
    1.07
    iados
    0.99
     meest
    0.99
     główn
    0.92
    если
    0.84
    i
    0.82
    ی
    0.82
    oa
    0.82
    cases
    0.80
    ে
    0.80
    POSITIVE LOGITS
    のは
    1.03
    zechoslovakia
    0.96
    ્રોલ
    0.91
     acetylcholine
    0.89
    UR
    0.88
    லாத
    0.86
    に
    0.86
     з
    0.85
    ẹn
    0.85
     সাহায্যে
    0.85
    Activations Density 0.819%

    No Known Activations