INDEX

Explanations

a wide range of positive sentiment words and words related to family and mythical beings, plus a mention of laundry.

oai_token-act-pair · gemini-2.0-flash

female persons

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

onViewCreated

-0.85

сылкі

-0.82

UnsafeEnabled

-0.81

abestanden

-0.75

esgue

-0.74

AnchorStyles

-0.73

Geplaatst

-0.71

 <=",

-0.70

ResumeLayout

-0.70

InputBorder

-0.69

POSITIVE LOGITS

she

1.05

 lady

1.04

 girl

1.04

Ms

1.02

 woman

0.96

 Girl

0.93

 female

0.93

Ms

0.90

 herself

0.90

 Lady

0.89

Activations Density 0.902%

a wide range of positive sentiment words and words related to family and mythical beings, plus a mention of laundry.

female persons

No Comments

No Known Activations