© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4853
    Prev
    Next
    INDEX
    Explanations

    closing curly brackets in code

    oai_token-act-pair · gemini-2.0-flash

    }

    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
     nakalista
    -1.08
     متعلقه
    -0.93
    ^(@)
    -0.91
     Monfieur
    -0.87
     autorytatywna
    -0.80
     continúas
    -0.80
     neceffary
    -0.80
     Jefus
    -0.79
    principalColumn
    -0.78
     Theſe
    -0.78
    POSITIVE LOGITS
     except
    0.59
    except
    0.56
     bes
    0.48
     save
    0.47
    ████
    0.46
     turn
    0.45
    Except
    0.45
    唯
    0.42
     kecuali
    0.42
     enc
    0.42
    Activations Density 0.478%

    No Known Activations