INDEX

Explanations

mentions of place names, events, and religious concepts, especially when related to Hinduism/India.

oai_token-act-pair · gemini-2.0-flash

variations of "itself"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

spaceBetween

-0.45

 textStatus

-0.44

気がします

-0.44

me

-0.43

UpInside

-0.42

 '*')

-0.42

気がする

-0.40

ola

-0.40

 defStyleAttr

-0.39

gued

-0.38

POSITIVE LOGITS

 itself

2.02

itself

1.73

 Itself

1.52

 stesso

1.29

 stessa

1.20

 ہی

1.18

 mismo

1.16

 ही

1.13

 misma

1.09

 itſelf

1.08

Activations Density 0.763%

mentions of place names, events, and religious concepts, especially when related to Hinduism/India.

variations of "itself"

No Comments

No Known Activations