INDEX

Explanations

scientific writing, involving suggesting, indicating, and confirming.

oai_token-act-pair · gemini-2.0-flash

suggests

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 studios

-0.60

 للمعارف

-0.57

TypedDataSet

-0.51

oredCriteria

-0.50

 Prä

-0.49

ButtonStyle

-0.47

Kens

-0.47

 anzunehmen

-0.47

ếp

-0.47

 مايو

-0.46

POSITIVE LOGITS

Tembelea

0.80

CppCodeGen

0.63

twimg

0.60

 cherchés

0.57

ьаж

0.55

 Meksiku

0.54

Parcelize

0.54

 EconPapers

0.52

Erreferentziak

0.49

EditorGUILayout

0.49

Activations Density 7.936%

scientific writing, involving suggesting, indicating, and confirming.

suggests

No Comments

No Known Activations