© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9229
    Prev
    Next
    INDEX
    Explanations

    GPT4

    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
    Negative Logits
    на
    2.88
    𝘢
    2.39
    𝘬
    2.26
    עת
    2.22
    रिडोर
    2.14
    𝘴
    2.13
    р
    2.09
    ▂
    2.05
    𝘪
    2.02
    as
    2.01
    POSITIVE LOGITS
     proxim
    2.37
     frente
    2.27
    !--
    2.25
     veuillez
    2.19
     toBe
    2.18
     quantifier
    2.18
     дума
    2.17
    ourcen
    2.15
    થી
    2.14
     furiously
    2.14
    Activations Density 0.036%

    No Known Activations