© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2002
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    /**
    -0.48
    はじめに
    -0.44
     ""],
    -0.43
    []
    -0.41
    [];
    -0.38
    ']],
    -0.38
    [])
    -0.37
    []):
    -0.37
    ADVERTISEMENT
    -0.36
    ModelSerializer
    -0.36
    POSITIVE LOGITS
    2
    0.72
    OGND
    0.66
    AndEndTag
    0.65
    PAIR
    0.65
    eradish
    0.63
     pairs
    0.61
    ecap
    0.60
    Pair
    0.59
    ällor
    0.59
     Barra
    0.58
    Activations Density 26.162%

    No Known Activations