INDEX

Explanations

substrings of numbers and punctuation that resemble URLs or citation codes

oai_token-act-pair · gemini-2.0-flash

URLs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 }}"></

-0.58

 step

-0.49

 rebut

-0.49

Erreferentziak

-0.45

pytest

-0.44

}</

-0.42

 malam

-0.40

step

-0.40

reszcie

-0.39

add

-0.39

POSITIVE LOGITS

PreferredItem

0.88

DebuggerNonUser

0.85

principalColumn

0.84

 ProtoMessage

0.77

fjspx

0.77

ItemBackground

0.69

AndEndTag

0.69

sizeCache

0.69

 beginnetje

0.68

 ویکی‌پدی

0.68

Activations Density 0.629%

substrings of numbers and punctuation that resemble URLs or citation codes

URLs

No Comments

No Known Activations