© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13668
    Prev
    Next
    INDEX
    Explanations

    stories and anecdotes related to the narrator's experiences with people

    oai_token-act-pair · gemini-2.0-flash

    Observing people in public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GraphicsUnit
    -0.58
    enseignements
    -0.51
    }();
    -0.50
     déchir
    -0.48
    '));
    -0.48
    لكتر
    -0.47
    ")));
    -0.47
     literaria
    -0.47
    Mozilla
    -0.47
    ggior
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.73
    localctx
    0.66
    ModelAdmin
    0.61
     незавершена
    0.60
     dads
    0.60
    期刊论文
    0.59
    RegistryLite
    0.59
     GenerationType
    0.58
     moms
    0.57
    #+#
    0.57
    Activations Density 2.982%

    No Known Activations