INDEX

Explanations

first-person narratives and descriptions of success or dreams.

oai_token-act-pair · gemini-2.0-flash

Personal narratives

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 betweenstory

-0.74

 ProtoMessage

-0.62

gese

-0.54

inSlope

-0.54

alde

-0.52

 كومونز

-0.52

hach

-0.52

 Patches

-0.51

 originalen

-0.51

లాలు

-0.51

POSITIVE LOGITS

存于互联网档案馆

0.66

 love

0.60

 fortfarande

0.57

love

0.56

LOVE

0.56

 invokingState

0.56

Diweddarwch

0.55

 IBOutlet

0.54

TextHelper

0.54

 LOVE

0.53

Activations Density 1.052%

first-person narratives and descriptions of success or dreams.

Personal narratives

No Comments

No Known Activations