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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11875
    Prev
    Next
    INDEX
    Explanations

    names of Polish locations, or possibly Polish names, and the letter J

    oai_token-act-pair · gemini-2.0-flash

    names and identifiers in data

    np_token-act-pair-logits · gpt-4o-mini

    J

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    j
    -0.53
    ELLE
    -0.45
    Insee
    -0.44
     whor
    -0.44
    ho
    -0.39
     vettoriale
    -0.38
    DebuggerStep
    -0.38
    stand
    -0.38
    Gemeinsame
    -0.36
    )))))
    -0.36
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
    存于互联网档案馆
    0.79
    CopyWith
    0.75
     MainAxisSize
    0.74
     ddelweddau
    0.72
     ModelExpression
    0.72
     كومونز
    0.71
    +#+
    0.69
     kasarigan
    0.69
    Lähteet
    0.69
    Activations Density 0.070%

    No Known Activations