© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13203
    Prev
    Next
    INDEX
    Explanations

    words with related to being in a bad situation or something negative.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    TagMode
    -0.80
    :+:
    -0.76
    #+#
    -0.75
    OGND
    -0.54
    InputBorder
    -0.54
    CppMethod
    -0.54
     PhpStorm
    -0.53
     Ferns
    -0.52
     Lectures
    -0.51
     Filling
    -0.50
    POSITIVE LOGITS
    Extinguishing
    0.59
    ngOnInit
    0.53
    ArrowToggle
    0.52
    entown
    0.51
     might
    0.50
    ActionMode
    0.50
    Diwedd
    0.50
    PyTuple
    0.49
    InvalidProtocol
    0.49
    ngOnDestroy
    0.48
    Activations Density 2.335%

    No Known Activations