INDEX

Explanations

abbreviations and acronyms, especially those in scientific contexts, possibly related to blood or immunology

oai_token-act-pair · gemini-2.0-flash

scientific assays and research

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

SSA

-1.09

TPA

-1.06

MSA

-0.99

HSA

-0.98

 CASA

-0.97

PIA

-0.97

ASA

-0.96

DLA

-0.96

ECA

-0.96

ARA

-0.94

POSITIVE LOGITS

SerializedSize

0.50

 trasmissione

0.49

 pegatina

0.49

 coleção

0.45

 delegación

0.44

 transmissão

0.44

 missão

0.44

 galería

0.44

 manifestazione

0.43

AccessorTable

0.42

Activations Density 0.724%

abbreviations and acronyms, especially those in scientific contexts, possibly related to blood or immunology

scientific assays and research

No Comments

No Known Activations