INDEX

Explanations

texts regarding international political attacks and poisonings involving Russia

oai_token-act-pair · gemini-2.0-flash

Russia attack or poisoning

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 üzere

-0.44

EMIA

-0.43

研究

-0.42

-0.40

ณา

-0.40

Im

-0.39

 Lucifer

-0.38

 Rhein

-0.38

POSITIVE LOGITS

AndEndTag

1.00

 InputDecoration

0.86

Portail

0.82

 JpaRepository

0.82

findpost

0.82

 يتيمه

0.81

LookAnd

0.81

 resourceCulture

0.81

CloseOperation

0.80

 otomatig

0.77

Activations Density 2.875%

texts regarding international political attacks and poisonings involving Russia

Russia attack or poisoning

No Comments

No Known Activations