INDEX

Explanations

German language and German-related proper nouns such as place names

oai_token-act-pair · gemini-2.0-flash

numeric and geographical terms

np_token-act-pair-logits · gpt-4o-mini

European languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hentet

-1.04

MigrationBuilder

-1.01

-0.86

 فريبيس

-0.85

 المعيارى

-0.83

 nahilalakip

-0.82

uxxxx

-0.81

IntoConstraints

-0.78

 AssemblyCulture

-0.77

urlpatterns

-0.77

POSITIVE LOGITS

0.49

gs

0.48

inde

0.43

ss

0.40

GS

0.40

com

0.40

-$

0.39

an

0.39

nan

0.39

Bew

0.39

Activations Density 0.290%

German language and German-related proper nouns such as place names

numeric and geographical terms

European languages

No Comments

No Known Activations