© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5646
    Prev
    Next
    INDEX
    Explanations

    movie review language, especially opinions with positive or negative sentiment

    oai_token-act-pair · gemini-2.0-flash

    Reviews

    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
     ویکی‌پدیای
    -0.68
    mobileqq
    -0.66
    }))
    -0.63
     Lepto
    -0.63
    UnknownFields
    -0.63
     onCancelled
    -0.61
     ]
    -0.60
    }],
    -0.60
     Hymen
    -0.59
     trefoil
    -0.59
    POSITIVE LOGITS
     plastiques
    0.46
     desgaste
    0.46
     normal
    0.46
     cérami
    0.45
    unggulan
    0.44
    endregion
    0.44
     viewType
    0.44
    zé
    0.43
     check
    0.43
    carnation
    0.43
    Activations Density 3.414%

    No Known Activations