© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12715
    Prev
    Next
    INDEX
    Explanations

    subjective language such as opinions.

    oai_token-act-pair · gemini-2.0-flash

    About Schleswig and Holstein

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Hentet
    -0.49
    setCharacter
    -0.44
     الدولى
    -0.40
    "]);
    -0.40
    putExtra
    -0.39
    ¡¡
    -0.39
    Ղ
    -0.37
    哦
    -0.36
     phạm
    -0.35
     waves
    -0.35
    POSITIVE LOGITS
    TagMode
    0.73
     виправивши
    0.66
    EDEFAULT
    0.66
     doInBackground
    0.65
    ArgsConstructor
    0.65
     InputDecoration
    0.63
    meral
    0.61
    |}{}
    0.60
     bezeichneter
    0.58
    AutoScaleMode
    0.58
    Activations Density 3.218%

    No Known Activations