© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11130
    Prev
    Next
    INDEX
    Explanations

    the word "from" and the words immediately following it

    oai_token-act-pair · gemini-2.0-flash

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     from
    -1.13
     FROM
    -1.11
     From
    -1.05
    from
    -1.04
    FROM
    -0.97
    From
    -0.96
     från
    -0.89
     dari
    -0.77
     desde
    -0.76
     từ
    -0.76
    POSITIVE LOGITS
    blaze
    0.65
    Rüyada
    0.63
     Jérusalem
    0.60
     Warszawie
    0.59
     bose
    0.59
     Busan
    0.59
     shogun
    0.58
     Nagasaki
    0.57
     Berber
    0.57
     Thebes
    0.57
    Activations Density 3.865%

    No Known Activations