© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11181
    Prev
    Next
    INDEX
    Explanations

    instances of locations combined with 'the'

    oai_token-act-pair · gemini-2.0-flash

    specific formatting or naming conventions in text

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

    the

    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
     تضيفلها
    -0.75
    +#+#
    -0.72
    يكب
    -0.63
    AddTagHelper
    -0.59
    MessageTagHelper
    -0.57
    kháu
    -0.57
    Nuorodos
    -0.56
    complexContent
    -0.56
    tvguidetime
    -0.56
     defStyle
    -0.54
    POSITIVE LOGITS
    Aholisi
    0.52
    SourceChecksum
    0.49
    ariado
    0.48
    (!_
    0.48
     "..\..\
    0.47
    {}'.
    0.46
    gée
    0.45
    fass
    0.45
    upassen
    0.45
     "..\..\..\
    0.45
    Activations Density 4.286%

    No Known Activations