INDEX

Explanations

conjunctions, prepositions, articles and adjectives with some frequency of use

oai_token-act-pair · gemini-2.0-flash

historical / legal texts

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

 المعيارى

-0.72

存于互联网档案馆

-0.69

GEBURTSDATUM

-0.67

TagMode

-0.66

StoryboardSegue

-0.65

AndEndTag

-0.61

 Exactos

-0.58

外部連結

-0.56

StructEnd

-0.56

PutMapping

-0.55

POSITIVE LOGITS

KURZBESCHREIBUNG

0.60

itals

0.46

plotlib

0.46

glLoad

0.42

LocationManager

0.41

허

0.41

loài

0.41

 Мексичка

0.41

envoi

0.40

essy

0.39

Activations Density 2.164%

conjunctions, prepositions, articles and adjectives with some frequency of use

historical / legal texts

No Comments

No Known Activations