© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14544
    Prev
    Next
    INDEX
    Explanations

    qualifiers that start with 'non-' or 'semi-' (and sometimes 'quasi')

    oai_token-act-pair · gemini-2.0-flash

    non

    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
    +#+#
    -0.78
    rungsseite
    -0.68
    脚注の使い方
    -0.61
    ImageContext
    -0.60
    +:+
    -0.59
     CURIAM
    -0.57
    <bos>
    -0.57
    crites
    -0.56
     createState
    -0.54
    MemoryWarning
    -0.54
    POSITIVE LOGITS
    overlapping
    0.66
    perturb
    0.60
    exponential
    0.59
    absorbing
    0.57
    asche
    0.56
    impossible
    0.54
    agricultural
    0.53
     Popov
    0.53
    面向
    0.52
    algorithmic
    0.52
    Activations Density 4.259%

    No Known Activations