© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10867
    Prev
    Next
    INDEX
    Explanations

    the word "from" near "the" and words ending with "s"

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -2.14
    from
    -1.94
    From
    -1.70
     FROM
    -1.66
     From
    -1.66
     desde
    -1.63
    FROM
    -1.62
    从
    -1.53
     dari
    -1.52
     từ
    -1.52
    POSITIVE LOGITS
     میلیارد
    0.40
    utete
    0.40
    CAPTION
    0.39
    gam
    0.38
    tements
    0.37
     sain
    0.36
     didReceive
    0.36
    やかに
    0.36
    ual
    0.35
     Verhältnisse
    0.35
    Activations Density 0.915%

    No Known Activations