© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2241
    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
    tive
    2.63
    ことです
    2.51
    lands
    2.47
    t
    2.47
    َ
    2.41
    ities
    2.39
    מת
    2.37
    ה
    2.36
    jenigen
    2.36
    是因为
    2.32
    POSITIVE LOGITS
    ឍ
    2.67
     misled
    2.66
    ⌓
    2.54
     <?=
    2.53
    isEqualTo
    2.51
    $;
    2.48
     букмекердик
    2.43
    Furthermore
    2.43
    ರ್ಯ
    2.38
    ങ്ങനെ
    2.37
    Activations Density 0.279%

    No Known Activations