INDEX

Explanations

words, phrases, and symbols used in political and legal text

oai_token-act-pair · gemini-2.0-flash

comma

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

GEBURTSDATUM

-0.53

 fieldNum

-0.53

tache

-0.44

hama

-0.42

 AssemblyTitle

-0.42

>>=

-0.41

 beginnetje

-0.41

verwijspagina

-0.39

platte

-0.39

tigt

-0.39

POSITIVE LOGITS

Sklici

0.68

AsUp

0.63

UrlResolution

0.59

SPATH

0.58

 terecht

0.58

 voren

0.57

createCanvas

0.57

CMAKE

0.57

($__

0.56

IGraphics

0.56

Activations Density 0.918%

words, phrases, and symbols used in political and legal text

comma

No Comments

No Known Activations