INDEX

Explanations

abbreviations for medical terms and truncated text

oai_token-act-pair · gemini-2.0-flash

ran

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

rachtet

-0.55

성

-0.55

 trop

-0.53

__':

-0.52

 mayor

-0.52

-0.51

gård

-0.50

VALOR

-0.50

 reported

-0.49

POSITIVE LOGITS

tagHelperRunner

1.03

 propOrder

0.93



0.92

 كومونز

0.89

 Diſ

0.88

 autorytatywna

0.86

 houſe

0.86

AnchorStyles

0.85

BeginContext

0.85

ScopeManager

0.84

Activations Density 1.486%

abbreviations for medical terms and truncated text

ran

No Comments

No Known Activations