© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6016
    Prev
    Next
    INDEX
    Explanations

    words expressing feelings and opinions

    oai_token-act-pair · gemini-2.0-flash

    friendliness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    GeoNames
    -0.54
     setuptools
    -0.53
     AttributeSet
    -0.53
    rawtypes
    -0.53
    }))
    -0.52
    ]){
    -0.51
    ьаж
    -0.50
    exclu
    -0.50
    aarrggbb
    -0.49
     SwitchCompat
    -0.49
    POSITIVE LOGITS
     friendly
    1.41
    friendly
    1.13
     polite
    1.12
     nice
    1.11
     Friendly
    1.10
    Friendly
    1.10
    nice
    1.04
     vriende
    1.02
     FRIEND
    0.98
     friendliness
    0.93
    Activations Density 0.651%

    No Known Activations