© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11564
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and opinions, often in response to a specific thing

    oai_token-act-pair · gemini-2.0-flash

    Comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    occuper
    -0.53
     W
    -0.50
     porte
    -0.49
     my
    -0.48
     Mar
    -0.44
     cam
    -0.44
    burgo
    -0.43
    '
    -0.42
    "
    -0.41
    W
    -0.40
    POSITIVE LOGITS
     ujednoznacz
    0.99
     GenerationType
    0.83
    PerformLayout
    0.81
    ]")]
    0.77
     دیکھیے
    0.76
    IsMutable
    0.75
     ]
    0.75
    StoryboardSegue
    0.75
     Monfieur
    0.74
     tartalomajánló
    0.73
    Activations Density 11.484%

    No Known Activations