© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1911
    Prev
    Next
    INDEX
    Explanations

    the context of publications about HIV research

    oai_token-act-pair · gemini-2.0-flash

    HIV

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    SequentialGroup
    -0.59
     referenties
    -0.54
    Архівовано
    -0.53
    ondissement
    -0.52
    rungsseite
    -0.51
    homonymie
    -0.51
    )];
    -0.50
     nakalista
    -0.50
     ]
    -0.50
    Aholisi
    -0.50
    POSITIVE LOGITS
    usermodel
    0.56
    COUVER
    0.56
    MENAFN
    0.53
     صوتيه
    0.53
    ExecuteReader
    0.52
    şiv
    0.52
     onCancelled
    0.50
    üle
    0.49
    OneToOne
    0.49
     Condition
    0.48
    Activations Density 11.126%

    No Known Activations