INDEX

Explanations

the word "animal" and related species.

oai_token-act-pair · gemini-2.0-flash

animal

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

ſelf

-1.19

 ſeveral

-1.13

 Jefus

-1.13

 myſelf

-1.10

 pleaſure

-1.03

 Reſ

-1.03

 doubtnut

-1.03

 Monfieur

-1.02

 themſelves

-1.01

Efq

-1.00

POSITIVE LOGITS

 sebe

0.39

Mar

0.37

Mar

0.35

ona

0.34

sou

0.33

рона

0.33

in

0.32

del

0.32

Activations Density 1.925%

the word "animal" and related species.

animal

No Comments

No Known Activations