INDEX

Explanations

words that indicate a judgmental or critical tone, specifically negativity but also self-congratulation.

oai_token-act-pair · gemini-2.0-flash

gibberish or code-related terms

np_token-act-pair-logits · gemini-2.0-flash

Formal, analytical writing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 équi

-0.59

capacidad

-0.54

praš

-0.54

ramine

-0.54

∭

-0.53

ALLENG

-0.52

Източници

-0.51

 abstrato

-0.51

ichier

-0.50

 impacting

-0.50

POSITIVE LOGITS

httphttps

0.53

migrationBuilder

0.51

CodeDom

0.50

tagext

0.49

AsUp

0.48

RegressionTest

0.48

/***/

0.47

inafter

0.46

Демографія

0.46

olism

0.45

Activations Density 2.236%

words that indicate a judgmental or critical tone, specifically negativity but also self-congratulation.

gibberish or code-related terms

Formal, analytical writing

No Comments

No Known Activations