© 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. 12587
    Prev
    Next
    INDEX
    Explanations

    percentages, especially those related to statistics and study results

    oai_token-act-pair · gemini-2.0-flash

    say "%"

    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
    __":
    -0.83
     kasarigan
    -0.83
    __':
    -0.82
    Билгалдахарш
    -0.82
    "])
    -0.81
    EDEFAULT
    -0.80
    ']))
    -0.79
    '])
    -0.77
    ]})
    -0.77
    __':
    -0.73
    POSITIVE LOGITS
     setuptools
    0.36
    стями
    0.35
     devices
    0.35
    č
    0.33
     Bancroft
    0.33
     Lue
    0.32
     Euse
    0.32
    listdir
    0.32
     Reverso
    0.32
     PHD
    0.32
    Activations Density 2.802%

    No Known Activations