INDEX

Explanations

a variety of seemingly unrelated word fragments and proper nouns

oai_token-act-pair · gemini-2.0-flash

say "Br" words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

Personendaten

-0.82

 الحره

-0.79

 kasarigan

-0.77

 للمعارف

-0.77

Portail

-0.75

protoimpl

-0.75

 صوتيه

-0.72

InjectAttribute

-0.72

 autorytatywna

-0.69

 <=",

-0.68

POSITIVE LOGITS

Dre

0.72

bro

0.71

bra

0.69

bru

0.69

DRE

0.68

Bra

0.67

Kra

0.67

dre

0.66

cro

0.66

Tre

0.66

Activations Density 5.767%

a variety of seemingly unrelated word fragments and proper nouns

say "Br" words

No Known Activations