© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4767
    Prev
    Next
    INDEX
    Explanations

    words relating to conflict, destruction, or revenge

    oai_token-act-pair · gemini-2.0-flash

    Fantasy storylines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    KommentareTeilen
    -0.65
     NSCoder
    -0.54
     numberOfRows
    -0.50
    AddTagHelper
    -0.50
     colspan
    -0.50
     melu
    -0.46
     StatelessWidget
    -0.46
     cinta
    -0.45
    +"\
    -0.44
    LookAnd
    -0.43
    POSITIVE LOGITS
    новниш
    0.60
    illance
    0.52
    RTLD
    0.51
    }));
    0.50
    السكان
    0.49
    UnusedPrivate
    0.49
    uttering
    0.48
     CWE
    0.47
    }))
    0.46
    mega
    0.46
    Activations Density 30.848%

    No Known Activations