INDEX

Explanations

personal pronouns (she/her/herself), proper nouns with titles (queen, mayor), names of ships, and/or references to dates with a year

oai_token-act-pair · gemini-2.0-flash

She

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 herself

-1.73

she

-1.41

herself

-1.21

she

-1.14

her

-1.03

protoimpl

-1.02

 그녀

-1.02

 shes

-1.00

但她

-0.98

She

-0.96

POSITIVE LOGITS

 himself

1.13

himself

0.78

his

0.76

 Himself

0.73

 који

0.68

 koji

0.68

his

0.62

 seine

0.57

 istrinya

0.54

 seiner

0.52

Activations Density 0.446%

personal pronouns (she/her/herself), proper nouns with titles (queen, mayor), names of ships, and/or references to dates with a year

She

No Comments

No Known Activations