© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15996
    Prev
    Next
    INDEX
    Explanations

    general common words and prepositions

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rawDesc
    -0.89
     RIPRODUZIONE
    -0.81
    DispatchToProps
    -0.81
    twimg
    -0.79
     jadx
    -0.76
     محفوظة
    -0.75
     getArguments
    -0.74
    Παραπομπές
    -0.73
     fhall
    -0.72
    cshtml
    -0.71
    POSITIVE LOGITS
    HtmlAttribute
    0.47
    ]`
    0.44
    expandindo
    0.40
     >=",
    0.39
    #+#
    0.35
     freakin
    0.35
     kasarigan
    0.35
     】
    0.34
     esat
    0.34
    vernote
    0.34
    Activations Density 5.449%

    No Known Activations