INDEX

Explanations

the word "adult" followed by words relating to the later stages of life

oai_token-act-pair · gemini-2.0-flash

adult

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

lismo

-0.61

oys

-0.60

cibles

-0.60

stander

-0.60

Affirmed

-0.58

omeness

-0.58

Климат

-0.56

Demografie

-0.55

cibility

-0.54

 adulthood

-0.54

POSITIVE LOGITS

0.97

 متعلقه

0.94

 leçons

0.83

addPreferredGap

0.82

 normaux

0.75

 recibo

0.75

 vérit

0.75

SequentialGroup

0.73



0.72

 courbe

0.69

Activations Density 0.636%

the word "adult" followed by words relating to the later stages of life

adult

No Comments

No Known Activations