© 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. 12154
    Prev
    Next
    INDEX
    Explanations

    the keyword "this" and words related to ownership

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act · 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
    this
    -1.90
    THIS
    -0.93
    these
    -0.91
    that
    -0.91
    his
    -0.84
    there
    -0.84
    it
    -0.76
    This
    -0.76
    then
    -0.76
    they
    -0.72
    POSITIVE LOGITS
    expandindo
    1.11
    帖最后由
    0.91
    ########.
    0.82
    saraba
    0.81
    Clik
    0.79
    Portály
    0.78
    oa̍t
    0.78
     RIPRODUZIONE
    0.77
    findpost
    0.75
    +#+
    0.74
    Activations Density 3.056%

    No Known Activations