© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13769
    Prev
    Next
    INDEX
    Explanations

    segments of dialog or social commentary that contain conflict, judgment, or negative behavior.

    oai_token-act-pair · gemini-2.0-flash

    negative interactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     дописавши
    -0.60
    emang
    -0.54
    #+#
    -0.51
     tartalomajánló
    -0.50
    ESOME
    -0.49
     مرئيه
    -0.49
     Prompt
    -0.47
     Yoko
    -0.46
    GEBURTS
    -0.46
    WarningLevel
    -0.46
    POSITIVE LOGITS
    awtextra
    0.69
    Revenir
    0.66
    DotNetBar
    0.63
     defaultstate
    0.60
     doInBackground
    0.59
    帖最后由
    0.56
    AndEndTag
    0.54
    قایناق‌لار
    0.53
    LayoutStyle
    0.52
    Tikang
    0.52
    Activations Density 9.999%

    No Known Activations