INDEX

Explanations

the word "central" or "Central"

oai_token-act-pair · gemini-2.0-flash

central

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

<bos>

-0.63

 InputDecoration

-0.56

htë

-0.53

 Italijani

-0.50

IntoConstraints

-0.50

 argint

-0.49

AutoScaleMode

-0.49

]))

-0.48

 pector

-0.47

 дописавши

-0.47

POSITIVE LOGITS

isés

0.56

inergic

0.56

isée

0.55

avax

0.54

metrist

0.50

 подо

0.49

znej

0.48

Pyx

0.48

manjaro

0.48

AZIONI

0.48

Activations Density 0.701%

the word "central" or "Central"

central

No Comments

No Known Activations